Updatify / Ollama | Release notes

What’s Changed

• Gemma 4 Tool Calling improvements
• Added latest models to Ollama App
• OpenClaw fixes for launching TUI

Full Changelog: https://github.com/ollama/ollama/compare/v0.20.2…v0.20.3

What’s Changed

• app: default app home view to new chat instead of launch by @jmorganca in https://github.com/ollama/ollama/pull/15312

Full Changelog: https://github.com/ollama/ollama/compare/v0.20.1…v0.20.2

Gemma 4

Effective 2B (E2B)

ollama run gemma4:e2b

Effective 4B (E4B)

ollama run gemma4:e4b

26B (Mixture of Experts model with 4B active parameters)

ollama run gemma4:26b

31B (Dense)

ollama run gemma4:31b

What’s Changed

• docs: update pi docs by @ParthSareen in https://github.com/ollama/ollama/pull/15152
• mlx: respect tokenizer add_bos_token setting in pipeline by @dhiltgen in https://github.com/ollama/ollama/pull/15185
• tokenizer: add SentencePiece-style BPE support by @dhiltgen in https://github.com/ollama/ollama/pull/15162

Full Changelog: https://github.com/ollama/ollama/compare/v0.19.0…v0.20.0-rc0

Ollama is now powered by MLX on Apple Silicon in preview

Ollama on Apple silicon is now built on top of Apple’s machine learning framework, MLX, to take advantage of its unified memory architecture.

https://github.com/user-attachments/assets/600297b0-3167-46a5-8e3a-fefda3a51b84

Read more: https://ollama.com/blog/mlx

What’s Changed

• Ollama’s app will now no longer incorrectly show “model is out of date”
• ollama launch pi now includes web search plugin that uses Ollama’s web search
• Improved KV cache hit rate when using the Anthropic-compatible API
• Fixed tool call parsing issue with Qwen3.5 where tool calls would be output in thinking
• MLX runner will now create periodic snapshots during prompt processing
• Fixed KV cache snapshot memory leak in MLX runner
• Fixed issue where flash attention would be incorrectly enabled for grok models
• Fixed qwen3-next:80b not loading in Ollama

New Contributors

• @amatas made their first contribution in https://github.com/ollama/ollama/pull/15022

Full Changelog: https://github.com/ollama/ollama/compare/v0.18.3…v0.19.0

What’s Changed

• ggml: force flash attention off for grok by @rick-github in https://github.com/ollama/ollama/pull/15050
• mlx: fix KV cache snapshot memory leak by @jessegross in https://github.com/ollama/ollama/pull/15065
• mlxrunner: schedule periodic snapshots during prefill by @jessegross in https://github.com/ollama/ollama/pull/15058
• doc: update vscode doc by @hoyyeva in https://github.com/ollama/ollama/pull/15064

Full Changelog: https://github.com/ollama/ollama/compare/v0.18.3…v0.18.4-rc0

Visual Studio Code

Microsoft Visual Studio Code now directly integrates with Ollama via GitHub Copilot.

If you have Ollama installed, any local or cloud model from Ollama can be selected for use within visual studio code.

What’s Changed

• GLM parser improvements for tool calls
• OpenClaw integration improvements for gateway checks

Full Changelog: https://github.com/ollama/ollama/compare/v0.18.2…v0.18.3

What’s Changed

• Add extra check to ensure npm and git are installed before installing OpenClaw
• Claude Code will now be faster when run locally, due to preventing cache breakages
• Fix to correctly support ollama launch openclaw --model <model>
• Register Ollama’s websearch package correctly for OpenClaw

Full Changelog: https://github.com/ollama/ollama/compare/v0.18.1…v0.18.2

Web Search and Fetch in OpenClaw

Ollama now ships with web search and web fetch plugin for OpenClaw. This allows Ollama’s models (local or cloud) to search the web for the latest content and news. This also allows OpenClaw with Ollama to be able to fetch the web and extract readable content for processing. This feature does not execute JavaScript.

When using local models with web search in OpenClaw, ensure you are signed into Ollama with ollama signin

ollama launch openclaw

You can install web search directly into OpenClaw as a plugin if you already have OpenClaw configured and working:

Ollama web search plugin

openclaw plugins install @ollama/openclaw-web-search

Non-interactive (headless) mode for ollama launch

ollama launch can now run in non-interactive mode.

Perfect for:

• Docker/containers: spin up an integration as a pipeline step to run evals, test prompts, or validate model behavior as part of your build. Tear it down when the job ends.

• CI/CD: Generate code reviews, security checks, and other tasks within your CI

• Scripts/automation: Kick off automated tasks with Ollama and claude code

• --model must be specified to run in headless mode

• --yes flag will auto-pull the model and skip any selectors

Try with: ollama launch claude --model kimi-k2.5:cloud --yes -- -p "how does this repository work?"

Use non-interactive mode in OpenClaw

Ollama 0.18 includes improved performance for OpenClaw and Ollama’s cloud models, including the new Nemotron-3-Super model by NVIDIA designed for high-performance agentic reasoning tasks.

Improved OpenClaw performance with Kimi-K2.5

This release of Ollama improves performance of cloud models and their reliability.

• Up to 2x faster speeds with Kimi-K2.5
• Tool calling accuracy has been improved

ollama launch openclaw --model kimi-k2.5

Ollama is now a provider in OpenClaw

Ollama can now be selected as an authentication and model provider during OpenClaw onboarding (thanks @BruceMacD for contributing and @steipete for reviewing!)

openclaw onboard --auth-choice ollama

More information: https://docs.openclaw.ai/providers/ollama

Nemotron-3-Super

Nemotron-3-Super: is a new 122B parameter model with strong reasoning and tool calling capability, while having top performance when run on modern hardware:

• ollama run nemotron-3-super:cloud
• ollama run nemotron-3-super to run locally (requires 96GB+ of VRAM)

Nemotron-3-Super scores highest of any open model on PinchBench, a benchmark suite that measures how successful models are at completing tasks when used with OpenClaw.

ollama launch openclaw --model nemotron-3-super:cloud

Or using OpenClaw’s onboarding:

What’s Changed

• parsers: repair unclosed arg_value tags in GLM tool calls by @BruceMacD in https://github.com/ollama/ollama/pull/14656
• Reapply “don’t require pulling stubs for cloud models” again by @jmorganca in https://github.com/ollama/ollama/pull/14608
• docs: format compat docs by @mxyng in https://github.com/ollama/ollama/pull/14678
• create: fix localhost handling by @dhiltgen in https://github.com/ollama/ollama/pull/14681
• build: smarter docker parallelism by @dhiltgen in https://github.com/ollama/ollama/pull/14653
• mlx: int4 groupsize 64 by @pdevine in https://github.com/ollama/ollama/pull/14682
• cloud_proxy: handle stream disconnects gracefully by @drifkin in https://github.com/ollama/ollama/pull/14685
• x/mlxrunner: replace sampler interface chain with single stateful Sampler by @pdevine in https://github.com/ollama/ollama/pull/14652
• rocm: update linux to v7.2 by @dhiltgen in https://github.com/ollama/ollama/pull/14391
• app: fix reset to defaults disabling auto-update by @hoyyeva in https://github.com/ollama/ollama/pull/14741
• mlx: get parameters from modelfile during model creation by @pdevine in https://github.com/ollama/ollama/pull/14747
• MLX: add header vendoring and remove go build tag by @dhiltgen in https://github.com/ollama/ollama/pull/14642
• ci: Fix windows build by @dhiltgen in https://github.com/ollama/ollama/pull/14754

Full Changelog: https://github.com/ollama/ollama/compare/v0.17.7…v0.17.8-rc1

What’s Changed

• Allow thinking levels such as "medium" to correctly interpreted in Ollama’s API for all thinking models
• Add context length to support compaction when using ollama launch

Full Changelog: https://github.com/ollama/ollama/compare/v0.17.6…v0.17.7

What’s Changed

• Fixed issue where GLM-OCR would not work due to incorrect prompt rendering
• Fixed tool calling parsing and rendering for Qwen 3.5 models

New Contributors

• @Victor-Quqi made their first contribution in https://github.com/ollama/ollama/pull/14584

Full Changelog: https://github.com/ollama/ollama/compare/v0.17.5…v0.17.6

New models

• Qwen3.5: the small Qwen 3.5 model series is now available in 0.8B, 2B, 4B and 9B parameter sizes.

What’s Changed

• Fixed crash in Qwen 3.5 models when split over GPU & CPU
• Fixed issue where Qwen 3.5 models would repeat themselves due to no presence penalty (note: you may have to redownload the qwen3.5 models: ollama pull qwen3.5:35b for example)
• ollama run --verbose will now show peak memory usage when using Ollama’s MLX engine
• Fixed memory issues and crashes in MLX runner
• Fixed issue where Ollama would not be able to run models imported from Qwen3.5 GGUF files

Full Changelog: https://github.com/ollama/ollama/compare/v0.17.4…v0.17.5

New models

• Qwen 3.5: a family of open-source multimodal models that delivers exceptional utility and performance.
• LFM 2: LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.

Note: for users on 0.17.1, this version will not automatically update. Re-downloading is required to receive the latest version of Ollama.

What’s Changed

• Tool call indices will now be included in parallel tool calls

Full Changelog: https://github.com/ollama/ollama/compare/v0.17.3…v0.17.4

What’s Changed

• Fixed issue where tool calls in the Qwen 3 and Qwen 3.5 model families would not be parsed correctly if emitted during thinking

Full Changelog: https://github.com/ollama/ollama/compare/v0.17.2…v0.17.3

What’s Changed

• Fixed issue where Ollama’s app on Windows would crash when a new update has been downloaded

Full Changelog: https://github.com/ollama/ollama/compare/v0.17.1…v0.17.2

What’s Changed

• Nemotron architecture support in Ollama’s engine
• MLX engine now has improved memory usage
• Ollama’s app will now allow models that support tools to use web search capabilities
• Improved LFM2 and LFM2.5 models in Ollama’s engine
• ollama create will no longer default to affine quantization for unquantized models when using the MLX engine
• Added configuration for disabling automatic update downloading

Full Changelog: https://github.com/ollama/ollama/compare/v0.17.0…v0.17.1

OpenClaw

OpenClaw can now be installed and configured automatically via Ollama, making it the easiest way to get up and running with OpenClaw with open models like Kimi-K2.5, GLM-5, and Minimax-M2.5.

Get started

ollama launch openclaw

Web search in OpenClaw

When using cloud models, websearch is enabled - allowing OpenClaw to search the internet.

What’s Changed

• Improved tokenizer performance
• Ollama’s macOS and Windows apps will now default to a context length based on available VRAM

New Contributors

• @natl-set made their first contribution in https://github.com/ollama/ollama/pull/14322

Full Changelog: https://github.com/ollama/ollama/compare/v0.16.3…v0.17.0

What’s Changed

• New ollama launch cline added for the Cline CLI
• ollama launch <integration> will now always show the model picker
• Added Gemma 3, Llama and Qwen 3 architectures to MLX runner

New Contributors

• @hellosaumil made their first contribution in https://github.com/ollama/ollama/pull/14271

Full Changelog: https://github.com/ollama/ollama/compare/v0.16.2…v0.16.3

What’s Changed

• ollama launch claude now supports searching the web when using :cloud models
• Fixed rendering issue when running ollama in PowerShell
• New setting in Ollama’s app makes it easier to disable cloud models for sensitive and private tasks where data cannot leave your computer. For Linux or when running ollama serve manually, set OLLAMA_NO_CLOUD=1.
• Fixed issue where experimental image generation models would not run in 0.16.0 and 0.16.1

Full Changelog: https://github.com/ollama/ollama/compare/v0.16.1…v0.16.2-rc0

What’s Changed

• Installing Ollama via the curl install script on macOS will now only prompt for your password if its required
• Installing Ollama via the iem install script in Windows will now show progress
• Image generation models will now respect the OLLAMA_LOAD_TIMEOUT variable

Full Changelog: https://github.com/ollama/ollama/compare/v0.16.0…v0.16.1

New models

• GLM-5: A strong reasoning and agentic model from Z.ai with 744B total parameters (40B active), built for complex systems engineering and long-horizon tasks.
• MiniMax-M2.5: a new state-of-the-art large language model designed for real-world productivity and coding tasks.

New ollama

The new ollama command makes it easy to launch your favorite apps with models using Ollama

What’s Changed

• Launch Pi with ollama launch pi
• Improvements to Ollama’s MLX runner to support GLM-4.7-Flash
• Ctrl+G will now allow for editing text prompts in a text editor when running a model

Full Changelog: https://github.com/ollama/ollama/compare/v0.15.6…v0.16.0

What’s Changed

• Fixed context limits when running ollama launch droid
• ollama launch will now download missing models instead of erroring
• Fixed bug where ollama launch claude would cause context compaction when providing images

Full Changelog: https://github.com/ollama/ollama/compare/v0.15.5…v0.15.6

New models

• Qwen3-Coder-Next: a coding-focused language model from Alibaba’s Qwen team, optimized for agentic coding workflows and local development.
• GLM-OCR: GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.

Improvements to ollama launch

• ollama launch can now be provided arguments, for example ollama launch claude -- --resume
• ollama launch will now work run subagents when using ollama launch claude
• Ollama will now set context limits for a set of models when using ollama launch opencode

What’s Changed

• Sub-agent support for ollama launch for planning, deep research, and similar tasks
• ollama signin will now open a browser window to make signing in easier
• Ollama will now default to the following context lengths based on VRAM:
  • < 24 GiB VRAM: 4,096 context
  • 24-48 GiB VRAM: 32,768 context
  • &gt;= 48 GiB VRAM: 262,144 context
• GLM-4.7-Flash support on Ollama’s experimental MLX engine
• ollama signin will now open the browser to the connect page
• Fixed off by one error when using num_predict in the API
• Fixed issue where tokens from a previous sequence would be returned when hitting num_predict

New Contributors

• @avukmirovich made their first contribution in https://github.com/ollama/ollama/pull/13934

What’s Changed

• ollama launch openclaw will now enter the standard OpenClaw onboarding flow if this has not yet been completed.

Full Changelog: https://github.com/ollama/ollama/compare/v0.15.3…v0.15.4

What’s Changed

• Renamed ollama launch clawdbot to ollama launch openclaw to reflect the project’s new name
• Improved tool calling for Ministral models
• docs: add clawdbot by @ParthSareen in https://github.com/ollama/ollama/pull/13925
• cmd/config: Use envconfig.Host() for base API in launch config packages by @gabe-l-hart in https://github.com/ollama/ollama/pull/13937
• ollama launch will now use the value of OLLAMA_HOST when running it

New Contributors

• @MBerguer made their first contribution in https://github.com/ollama/ollama/pull/13971
• @taronsung made their first contribution in https://github.com/ollama/ollama/pull/13965
• @noureldin-azzab made their first contribution in https://github.com/ollama/ollama/pull/13961
• @dhirajlochib made their first contribution in https://github.com/ollama/ollama/pull/13645
• @ThanhNguyxn made their first contribution in https://github.com/ollama/ollama/pull/13979

Full Changelog: https://github.com/ollama/ollama/compare/v0.15.2…v0.15.3

What’s Changed

• New ollama launch clawdbot command for launching Clawdbot using Ollama models

Full Changelog: https://github.com/ollama/ollama/compare/v0.15.1…v0.15.2

What’s Changed

• GLM-4.7-Flash performance and correctness improvements, fixing repetitive answers and tool calling quality
• Fixed performance issues on macOS and arm64 Linux
• Fixed issue where ollama launch would not detect claude and would incorrectly update opencode configurations

New Contributors

• @stillhart made their first contribution in https://github.com/ollama/ollama/pull/13855

Full Changelog: https://github.com/ollama/ollama/compare/v0.15.0…v0.15.1

ollama launch

A new ollama launch command to use Ollama’s models with Claude Code, Codex, OpenCode, and Droid without separate configuration.

What’s Changed

• New ollama launch command for Claude Code, Codex, OpenCode, and Droid
• Fixed issue where creating multi-line strings with """ would not work when using ollama run
• <kbd>Ctrl</kbd>+<kbd>J</kbd> and <kbd>Shift</kbd>+<kbd>Enter</kbd> now work for inserting newlines in ollama run
• Reduced memory usage for GLM-4.7-Flash models

• Z-Image Turbo: 6 billion parameter text-to-image model from Alibaba’s Tongyi Lab. It generates high-quality photorealistic images.
• Flux.2 Klein: Black Forest Labs’ fastest image-generation models to date.

New models

• GLM-4.7-Flash: As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.
• LFM2.5-1.2B-Thinking: LFM2.5 is a new family of hybrid models designed for on-device deployment.

What’s Changed

• Fixed issue where Ollama’s macOS app would interrupt system shutdown
• Fixed ollama create and ollama show commands for experimental models
• The /api/generate API can now be used for image generation
• Fixed minor issues in Nemotron-3-Nano tool parsing
• Fixed issue where removing an image generation model would cause it to first load
• Fixed issue where ollama rm would only stop the first model in the list if it were running

Full Changelog: https://github.com/ollama/ollama/compare/v0.14.2…v0.14.3

New models

• TranslateGemma: A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.

What’s Changed

• <kbd>Shift</kbd> + <kbd>Enter</kbd> (or <kbd>Ctrl</kbd> + <kbd>j</kbd>) will now enter a newline in Ollama’s CLI
• Improve /v1/responses API to better confirm to OpenResponses specification

New Contributors

• @yuhongsun96 made their first contribution in https://github.com/ollama/ollama/pull/13135
• @koaning made their first contribution in https://github.com/ollama/ollama/pull/13326

Full Changelog: https://github.com/ollama/ollama/compare/v0.14.1…v0.14.2

Image generation models (experimental)

Experimental image generation models are available for macOS and Linux (CUDA) in Ollama:

Available models

• Z-Image-Turbo

ollama run x/z-image-turbo

Note: x is a username on ollama.com where experimental models are uploaded

More models coming soon:

1. Qwen-Image-2512
2. Qwen-Image-Edit-2511
3. GLM-Image

What’s Changed

• fix macOS auto-update signature verification failure

New Contributors

• @joshxfi made their first contribution in https://github.com/ollama/ollama/pull/13711
• @maternion made their first contribution in https://github.com/ollama/ollama/pull/13709

Full Changelog: https://github.com/ollama/ollama/compare/v0.14.0…v0.14.1

What’s Changed

• ollama run --experimental CLI will now open a new Ollama CLI that includes an agent loop and the bash tool
• Anthropic API compatibility: support for the /v1/messages API
• A new REQUIRES command for the Modelfile allows declaring which version of Ollama is required for the model
• For older models, Ollama will avoid an integer underflow on low VRAM systems during memory estimation
• More accurate VRAM measurements for AMD iGPUs
• Ollama’s app will now highlight swift source code
• An error will now return when embeddings return NaN or -Inf
• Ollama’s Linux install bundles files now use zst compression
• New experimental support for image generation models, powered by MLX

New Contributors

• @Vallabh-1504 made their first contribution in https://github.com/ollama/ollama/pull/13550
• @majiayu000 made their first contribution in https://github.com/ollama/ollama/pull/13596
• @harrykiselev made their first contribution in https://github.com/ollama/ollama/pull/13615

Full Changelog: https://github.com/ollama/ollama/compare/v0.13.5…v0.14.0-rc2

New Models

• Google’s FunctionGemma a specialized version of Google’s Gemma 3 270M model fine-tuned explicitly for function calling.

What’s Changed

• bert architecture models now run on Ollama’s engine
• Added built-in renderer & tool parsing capabilities for DeepSeek-V3.1
• Fixed issue where nested properties in tools may not have been rendered properly

New Contributors

• @familom made their first contribution in https://github.com/ollama/ollama/pull/13220
• @nathannewyen made their first contribution in https://github.com/ollama/ollama/pull/13469

Full Changelog: https://github.com/ollama/ollama/compare/v0.13.4…v0.13.5

New Models

• Nemotron 3 Nano: A new Standard for Efficient, Open, and Intelligent Agentic Models
• Olmo 3 and Olmo 3.1: A series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.

What’s Changed

• Enable Flash Attention automatically for models by default
• Fixed handling of long contexts with Gemma 3 models
• Fixed issue that would occur with Gemma 3 QAT models or other models imported with the Gemma 3 architecture

New Contributors

• @familom made their first contribution in https://github.com/ollama/ollama/pull/13220

Full Changelog: https://github.com/ollama/ollama/compare/v0.13.3…v0.13.4-rc0

New models

• Devstral-Small-2: 24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
• rnj-1: Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.
• nomic-embed-text-v2: nomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval.

What’s Changed

• Improved truncation logic when using /api/embed and /v1/embeddings
• Extend Gemma 3 architecture to support rnj-1 model
• Fix error that would occur when running qwen2.5vl with image input

Full Changelog: https://github.com/ollama/ollama/compare/v0.13.2…v0.13.3

New models

• Qwen3-Next: The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.

What’s Changed

• Flash attention is now enabled by default for vision models such as mistral-3, gemma3, qwen3-vl and more. This improves memory utilization and performance when providing images as input.
• Fixed GPU detection on multi-GPU CUDA machines
• Fixed issue where deepseek-v3.1 would always think even with thinking is disabled in Ollama’s app

New Contributors

• @chengcheng84 made their first contribution in https://github.com/ollama/ollama/pull/13265
• @nathan-hook made their first contribution in https://github.com/ollama/ollama/pull/13256

Full Changelog: https://github.com/ollama/ollama/compare/v0.13.1…v0.13.2

New models

• Ministral-3: The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
• Mistral-Large-3: A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.

What’s Changed

• nomic-embed-text will now use Ollama’s engine by default
• Tool calling support for cogito-v2.1
• Fixed issues with CUDA VRAM discovery
• Fixed link to docs in Ollama’s app
• Fixed issue where models would be evicted on CPU-only systems
• Ollama will now better render errors instead of showing Unmarshal: errors
• Fixed issue where CUDA GPUs would fail to be detected with older GPUs
• Added thinking and tool parsing for cogito-v2.1

New Contributors

• @EntropyYue made their first contribution in https://github.com/ollama/ollama/pull/13237
• @kokes made their first contribution in https://github.com/ollama/ollama/pull/13231

Full Changelog: https://github.com/ollama/ollama/compare/v0.13.0…v0.13.1

New models

• DeepSeek-OCR: DeepSeek-OCR uses optical 2D mapping to compress long contexts, achieving high OCR precision with reduced vision tokens and demonstrating practical value in document processing.
• Cogito-V2.1: instruction tuned generative models, currently the best open-weight LLM by a US company

DeepSeek-OCR

DeepSeek-OCR is now available on Ollama. Example inputs:

ollama run deepseek-ocr "/path/to/image\n<|grounding|>Given the layout of the image."

ollama run deepseek-ocr "/path/to/image\nFree OCR."

ollama run deepseek-ocr "/path/to/image\nParse the figure."

ollama run deepseek-ocr "/path/to/image\nExtract the text in the image."

ollama run deepseek-ocr "/path/to/image\n<|grounding|>Convert the document to markdown."

New bench tool

Ollama’s GitHub repo now includes a bench tool that can be used to test model performance. For the time being this is a separate tool that can be built in the Ollama GitHub repository:

First, install Go. Then from the root of the Ollama repository run:

go run ./cmd/bench -model gpt-oss:20b

For more information see the tool’s documentation

What’s Changed

• DeepSeek-OCR is now supported
• DeepSeek-V3.1 architecture is now supported in Ollama’s engine

Logprobs

Ollama’s API and OpenAI-compatible API now support log probabilities. Log probabilities of output tokens indicate the likelihood of each token occurring in the sequence given the context. This is useful for different use cases:

1. Classification tasks
2. Retrieval (Q&A) evaluation
3. Autocomplete
4. Token highlighting and outputting bytes
5. Calculating perplexity

To enable Logprobs, provide "logprobs": true to Ollama’s API:

curl http://localhost:11434/api/generate -d '{
  "model": "gemma3",
  "prompt": "Why is the sky blue?",
  "logprobs": true
}'

When log probabilities are requested, response chunks will now include a "logprobs" field with the token, log probability and raw bytes (for partial unicode).

{
  "model": "gemma3",
  "created_at": "2025-11-14T22:17:56.598562Z",
  "response": "Okay",
  "done": false,
  "logprobs": [
    {
      "token": "Okay",
      "logprob": -1.3434503078460693,
      "bytes": [
        79,
        107,
        97,
        121
      ]
    }
  ]
}

top_logprobs

When setting "top_logprobs", a number of most-likely tokens are also provided, making it possible to introspect alternative tokens. Below is an example request.

curl http://localhost:11434/api/generate -d '{
  "model": "gemma3",
  "prompt": "Why is the sky blue?",
  "logprobs": true,
  "top_logprobs": 3
}'

ollama run now works with embedding models

ollama run can now run embedding models to generate vector embeddings from text:

ollama run embeddinggemma "Hello world"

Content can also be provided to ollama run via standard input:

echo "Hello world" | ollama run embeddinggemma

What’s Changed

• Fixed errors when running qwen3-vl:235b and qwen3-vl:235b-instruct
• Enable flash attention for Vulkan (currently needs to be built from source)
• Add Vulkan memory detection for Intel GPU using DXGI+PDH
• Ollama will now return tool call IDs from the /api/chat API
• Fixed hanging due to CPU discovery
• Ollama will now show login instructions when switching to a cloud model in interactive mode
• Fix reading stale VRAM data
• ollama run now works with embedding models

New Contributors

• @ryanycoleman made their first contribution in https://github.com/ollama/ollama/pull/11740
• @Rajathbail made their first contribution in https://github.com/ollama/ollama/pull/12929
• @virajwad made their first contribution in https://github.com/ollama/ollama/pull/12664
• @AXYZdong made their first contribution in https://github.com/ollama/ollama/pull/8601

Full Changelog: https://github.com/ollama/ollama/compare/v0.12.9…v0.12.10

What’s Changed

• Fix performance regression on CPU-only systems

Full Changelog: https://github.com/ollama/ollama/compare/v0.12.8…v0.12.9

What’s Changed

• qwen3-vl performance improvements, including flash attention support by default
• qwen3-vl will now output less leading whitespace in the response when thinking
• Fixed issue where deepseek-v3.1 thinking could not be disabled in Ollama’s new app
• Fixed issue where qwen3-vl would fail to interpret images with transparent backgrounds
• Ollama will now stop running a model before removing it via ollama rm
• Fixed issue where prompt processing would be slower on Ollama’s engine
• Ignore unsupported iGPUs when doing device discovery on Windows

New Contributors

• @athshh made their first contribution in https://github.com/ollama/ollama/pull/12822

Full Changelog: https://github.com/ollama/ollama/compare/v0.12.7…v0.12.8

New models

• Qwen3-VL: Qwen3-VL is now available in all parameter sizes ranging from 2B to 235B
• MiniMax-M2: a 230 Billion parameter model built for coding & agentic workflows available on Ollama’s cloud

Add files and adjust thinking levels in Ollama’s new app

Ollama’s new app now includes a way to add one or many files when prompting the model:

For better responses, thinking levels can now be adjusted for the gpt-oss models:

New API documentation

New API documentation is available for Ollama’s API: https://docs.ollama.com/api

What’s Changed

• Model load failures now include more information on Windows
• Fixed embedding results being incorrect when running embeddinggemma

What’s Changed

• Ollama’s app now supports searching when running DeepSeek-V3.1, Qwen3 and other models that support tool calling.
• Flash attention is now enabled by default for Gemma 3, improving performance and memory utilization
• Fixed issue where Ollama would hang while generating responses
• Fixed issue where qwen3-coder would act in raw mode when using /api/generate or ollama run qwen3-coder <prompt>
• Fixed qwen3-embedding providing invalid results
• Ollama will now evict models correctly when num_gpu is set
• Fixed issue where tool_index with a value of 0 would not be sent to the model

Experimental Vulkan Support

Experimental support for Vulkan is now available when you build locally from source. This will enable additional GPUs from AMD, and Intel which are not currently supported by Ollama. To build locally, install the Vulkan SDK and set VULKAN_SDK in your environment, then follow the developer instructions. In a future release, Vulkan support will be included in the binary release as well. Please file issues if you run into any problems.

New Contributors

• @yajianggroup made their first contribution in https://github.com/ollama/ollama/pull/12377
• @inforithmics made their first contribution in https://github.com/ollama/ollama/pull/11835

What’s Changed

• Thinking models now support structured outputs when using the /api/chat API
• Ollama’s app will now wait until Ollama is running to allow for a conversation to be started
• Fixed issue where "think": false would show an error instead of being silently ignored
• Fixed deepseek-r1 output issues
• macOS 12 Monterey and macOS 13 Ventura are no longer supported
• AMD gfx900 and gfx906 (MI50, MI60, etc) GPUs are no longer supported via ROCm. We’re working to support these GPUs via Vulkan in a future release.

New Contributors

• @shengxinjing made their first contribution in https://github.com/ollama/ollama/pull/12415

Full Changelog: https://github.com/ollama/ollama/compare/v0.12.4…v0.12.5-rc0

What’s Changed

• Flash attention is now enabled by default for Qwen 3 and Qwen 3 Coder
• Fixed minor memory estimation issues when scheduling models on NVIDIA GPUs
• Fixed an issue where keep_alive in the API would accept different values for the /api/chat and /api/generate endpoints
• Fixed tool calling rendering with qwen3-coder
• More reliable and accurate VRAM detection
• OLLAMA_FLASH_ATTENTION can now be overridden to 0 for models that have flash attention enabled by default
• macOS 12 Monterey and macOS 13 Ventura are no longer supported
• Fixed crash where templates were not correctly defined
• Fix memory calculations on NVIDIA iGPUs
• AMD gfx900 and gfx906 (MI50, MI60, etc) GPUs are no longer supported via ROCm. We’re working to support these GPUs via Vulkan in a future release.

New Contributors

• @Fachep made their first contribution in https://github.com/ollama/ollama/pull/12412

Full Changelog: https://github.com/ollama/ollama/compare/v0.12.3…v0.12.4-rc3

New models

• DeepSeek-V3.1-Terminus: DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode. It delivers more stable & reliable outputs across benchmarks compared to the previous version:

  Run on Ollama’s cloud:

  ollama run deepseek-v3.1:671b-cloud

  Run locally (requires 500GB+ of VRAM)

  ollama run deepseek-v3.1

• Kimi-K2-Instruct-0905: Kimi K2-Instruct-0905 is the latest, most capable version of Kimi K2. It is a state-of-the-art mixture-of-experts (MoE) language model, featuring 32 billion activated parameters and a total of 1 trillion parameters.

  ollama run kimi-k2:1t-cloud

What’s Changed

• Fixed issue where tool calls provided as stringified JSON would not be parsed correctly
• ollama push will now provide a URL to follow to sign in
• Fixed issues where qwen3-coder would output unicode characters incorrectly
• Fix issue where loading a model with /load would crash

New Contributors

• @gr4ceG made their first contribution in https://github.com/ollama/ollama/pull/12385

Full Changelog: https://github.com/ollama/ollama/compare/v0.12.2…v0.12.3

Web search

A new web search API is now available in Ollama. Ollama provides a generous free tier of web searches for individuals to use, and higher rate limits are available via Ollama’s cloud. This web search capability can augment models with the latest information from the web to reduce hallucinations and improve accuracy.

What’s Changed

• Models with Qwen3’s architecture including MoE now run in Ollama’s new engine
• Fixed issue where built-in tools for gpt-oss were not being rendered correctly
• Support multi-regex pretokenizers in Ollama’s new engine
• Ollama’s new engine can now load tensors by matching a prefix or suffix

Full Changelog: https://github.com/ollama/ollama/compare/v0.12.1…v0.12.2

New models

• Qwen3 Embedding: state of the art open embedding model by the Qwen team

What’s Changed

• Qwen3-Coder now supports tool calling
• Ollama’s app will now longer show “connection lost” in error when connecting to cloud models
• Fixed issue where Gemma3 QAT models would not output correct tokens
• Fix issue where & characters in Qwen3-Coder would not be parsed correctly when function calling
• Fixed issues where ollama signin would not work properly on Linux

Full Changelog: https://github.com/ollama/ollama/compare/v0.12.0…v0.12.1