Skip to content
VibekollenBETAVibekollen

Source

Ollama

108 items in the feed. The texts are the sources' own descriptions — the content belongs to Ollama.

ReleaseOllama

v0.40.11

What's Changed qwen3coder: preserve literal function closing tags in parameters by @hoyyeva in #19228 launch: use allocated context for OpenCode by @hoyyeva in #19193 decision: allow empty state for vllm-d3 by @SynapShift in #19173 llama.cpp: version bump b11845 by @dhiltgen in #19250 mlxrunner: spell out symbols, numbers and links for Phonon by @jmorganca in #19234 voice: add voice catalog for Phonon by @jmorganca in #19242 New Contributors @SynapShift made their first contribution in #19173 Full Changelog: v0.40.10...v0.40.11-rc0

24 Oct github.com

ReleaseOllama

v0.40.10: Update gemma renderers (#19241)

renderers: add gemma4-nemotron renderer Add a Gemma 4 renderer variant that renders assistant content before its tool calls rather than after the tool responses. Models opt in with RENDERER gemma4-nemotron; gemma4 auto-detection is unchanged. Adds the corresponding chat template as a test fixture for Jinja parity checks. mlx: support Gemma 4 targets with DFlash drafts Load a draft-owned output head when its config requires one, while preserving the target-head path used by existing DFlash models. Expose Gemma 4 hidden-state taps and raw logits for speculative decoding. Report safetensors target precision independently of quantized draft weights.

23 Oct github.com

ReleaseOllama

v0.40.9

Speech Ollama can now generate speech with Phonon on Apple Silicon. ollama run plays text or a chat model's reply aloud as the audio is generated, and apps can stream audio through the OpenAI-compatible /v1/audio/speech endpoint. ollama run phonon "Hello from Ollama." d3 decision models d3 brings vLLM Semantic Router's decision models to Ollama. Give a model text, structured state, or an image, and ask it to classify, answer yes or no, or score options with probabilities. The family includes 2B, 4B, 9B, and 27B sizes. ollama run d3 "A customer says their card was charged twice." --ask "Is this a billing issue?" Flint on Linux and Windows Flint now runs on Linux and Windows as well as macOS. Other improvements Streaming OpenAI Responses and Anthropic Messages requests now report generation failures instead of ending silently after partial output. ollama launch now passes cloud models' context lengths and capabilities to coding tools, fixing incorrect context and compaction settings. Anthropic-compatible web search now uses the model's supported thinking setting in follow-up requests, preventing avoidable failures. Full Changelog: v0.40.8...v0.40.9

23 Oct github.com

ReleaseOllama

v0.40.8

Recursive Flint Flint brings Recursive's coding model to Ollama. It is designed for the work coding agents do across a repository: understanding unfamiliar code, tracing bugs, implementing features, and adding tests. Reasoning, multi-turn tool use, and a 262K-token context window support longer tasks across files and tool interactions. Flint is an Apache 2.0-licensed, 40B-parameter mixture-of-experts model with approximately 2.5B parameters active per token. In its release evaluations, Recursive reports 54.9% on Terminal-Bench 2.1 and 74.2% on SWE-bench Verified. ollama run flint Note: rc0 supports Flint on MacOS. Other GPU support will be enabled in later RC builds. Full Changelog: v0.40.7...v0.40.8-rc0

21 Oct github.com

ReleaseOllama

v0.40.8: mlx: add Flint model support (#19181)

Preserve source tool JSON alongside decoded API values so Flint can retain numeric types and schema order in prompts. Existing API marshaling is unchanged. Assemble ModelOpt expert banks during safetensors import, and reject direct Flint NVFP4 creation before conversion. Other models retain their existing import and quantization paths. Add optional learned sinks and device causal masks to shared MLX attention. Existing callers retain the no-sink and host-mask paths; Flint opts into the new behavior.

21 Oct github.com

ReleaseOllama

v0.40.7

What's Changed pplx-decider is a 27B decision model from Perplexity, fine-tuned from Qwen3.8-27B Continuing an OpenAI-compatible Responses conversation no longer fails when switching between models with and without thinking, or when the history contains another provider's compaction items Fixed streaming Responses requests where client tool calls (e.g. Codex with web search) could emit before open reasoning items, producing misordered/duplicate tool call events Requests routed to remote models are now cancelled on ollama.com when the client disconnects, instead of continuing to run ollama show now reports which renderer and parser a model uses and where its chat template comes from; the API exposes the same values in new renderer, parser, and template_source fields More draft models now work with speculative decoding: llama-server infers the draft type automatically instead of requiring Ollama to identify it ollama launch claude now clamps CLAUDE_CODE_AUTO_COMPACT_WINDOW to Claude Code's supported range, avoiding a "window too large" warning Updated llama.cpp and MLX Full Changelog: v0.40.6...v0.40.7

21 Oct github.com

ReleaseOllama

v0.40.4

What's Changed llama: update llama.cpp to b11521 for decision models and EmbeddingGemma 2 by @jmorganca in #18917 server: reuse verified manifests and loaded models in inference routes by @dhiltgen in #18947 mlx: compact restored recurrent state after speculative rollback by @dhiltgen in #18955 launch: include installed models in Codex /model picker by @ParthSareen in #18887 MLX, MLX-C: version bump by @dhiltgen in #18956 Full Changelog: v0.40.3...v0.40.4-rc1

14 Oct github.com

ReleaseOllama

v0.40.4

What's Changed llama: update llama.cpp to b11521 for decision models and EmbeddingGemma 2 by @jmorganca in #18917 server: reuse verified manifests and loaded models in inference routes by @dhiltgen in #18947 mlx: compact restored recurrent state after speculative rollback by @dhiltgen in #18955 launch: include installed models in Codex /model picker by @ParthSareen in #18887 MLX, MLX-C: version bump by @dhiltgen in #18956 Full Changelog: v0.40.3...v0.40.4-rc1

13 Oct github.com

ReleaseOllama

v0.40.4

What's Changed llama: update llama.cpp to b11521 for decision models and EmbeddingGemma 2 by @jmorganca in #18917 server: reuse verified manifests and loaded models in inference routes by @dhiltgen in #18947 mlx: compact restored recurrent state after speculative rollback by @dhiltgen in #18955 launch: include installed models in Codex /model picker by @ParthSareen in #18887 MLX, MLX-C: version bump by @dhiltgen in #18956 Full Changelog: v0.40.3...v0.40.4-rc0

12 Oct github.com

ReleaseOllama

v0.40.1

What's Changed server: proxy cloud usage and balance APIs by @drifkin in #18829 llama: fix clef head reads past 2GiB on windows by @Gigrise in #18777 cmd: remove account step from CLI onboarding by @hoyyeva in #18826 manifest: avoid symlinks on Windows by @dhiltgen in #18852 docs: fix 6 dead links in README community integrations list by @aniketkrs in #18814 docs: fix broken download links in app README by @chenlichao in #18233 mlx: drop carried metal residency patch now that it is upstream by @dhiltgen in #18854 New Contributors @Gigrise made their first contribution in #18777 @aniketkrs made their first contribution in #18814 @chenlichao made their first contribution in #18233 Full Changelog: v0.40.0...v0.40.1-rc0

8 Oct github.com

ReleaseOllama

v0.35.0

What's Changed app: sync macOS update menu and icon at startup by @hoyyeva in #18622 app: defer Settings model discovery by @ParthSareen in #18598 app: isolate cloud-setting tests from Windows user config by @drifkin in #18626 api: deprecate typical_p by @dhiltgen in #18627 bench: use HumanEval patch prompts by @dhiltgen in #17480 feat: add System One scoring API by @ParthSareen in #18606 mlx: bound pull stall retries and let the watchdog interrupt them by @dhiltgen in #18625 Full Changelog: v0.34.4...v0.35.0-rc1

28 Sept github.com

ReleaseOllama

v0.34.4

What's Changed server: fix intermittent "model not found" errors. by @rick-github in #18438 server: apply structured outputs in a single pass on thinking models by @jessegross in #18479 app: avoid System Events for ChatGPT/Codex detection by @hoyyeva in #18601 llama.cpp: version update by @dhiltgen in #18577 MLX: version bump by @dhiltgen in #18576 mlx: select Gemma 4 image resolution dynamically by @dhiltgen in #18603 mlx: speed up Qwen 3.8 prompt processing by @dhiltgen in #18550 Full Changelog: v0.34.3...v0.34.4-rc0

24 Sept github.com

ReleaseOllama

v0.34.4

What's Changed server: fix intermittent "model not found" errors. by @rick-github in #18438 server: apply structured outputs in a single pass on thinking models by @jessegross in #18479 app: avoid System Events for ChatGPT/Codex detection by @hoyyeva in #18601 llama.cpp: version update by @dhiltgen in #18577 MLX: version bump by @dhiltgen in #18576 mlx: select Gemma 4 image resolution dynamically by @dhiltgen in #18603 mlx: speed up Qwen 3.8 prompt processing by @dhiltgen in #18550 Full Changelog: v0.34.3...v0.34.4-rc0

23 Sept github.com

ReleaseOllama

v0.34.1

What's Changed app: fix ChatGPT model selector spacing mlxrunner: Evict prefix cache snapshots from the active conversation mlxrunner: check system free memory and wait for evicted runners before loading the next MLX model llm: raise token repeat limit to 100 and return error instead of incomplete result mlx: scope array lifetimes instead of pinning and sweeping llm: keep gemma3n projector off the CPU app: refresh Apps layout and command copy feedback MLX and llama.cpp updates Full Changelog: v0.34.0...v0.34.1-rc1

15 Sept github.com

ReleaseOllama

v0.34.1

What's Changed app: fix ChatGPT model selector spacing mlxrunner: Evict prefix cache snapshots from the active conversation mlxrunner: check system free memory and wait for evicted runners before loading the next MLX model llm: raise token repeat limit to 100 and return error instead of incomplete result mlx: scope array lifetimes instead of pinning and sweeping llm: keep gemma3n projector off the CPU app: refresh Apps layout and command copy feedback MLX and llama.cpp updates Full Changelog: v0.34.0...v0.34.1-rc1

15 Sept github.com

ReleaseOllama

v0.34.0

Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS. This release also improves structured output performance on Apple Silicon, adds support for OpenAI-compatible client tool search and response compaction, and makes images work correctly through compacted responses. Full Changelog: v0.33.3...v0.34.0-rc1

10 Sept github.com

ReleaseOllama

v0.34.0

Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS. This release also improves structured output performance on Apple Silicon, adds support for OpenAI-compatible client tool search and response compaction, and makes images work correctly through compacted responses. Full Changelog: v0.33.3...v0.34.0-rc1

9 Sept github.com

ReleaseOllama

v0.34.0

Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS. This release also improves structured output performance on Apple Silicon, adds support for OpenAI-compatible client tool search and response compaction, and makes images work correctly through compacted responses. Full Changelog: v0.33.3...v0.34.0-rc1

9 Sept github.com

ReleaseOllama

v0.34.0

Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS. This release also improves structured output performance on Apple Silicon, adds support for OpenAI-compatible client tool search and response compaction, and makes images work correctly through compacted responses. Full Changelog: v0.33.3...v0.34.0-rc1

9 Sept github.com

ReleaseOllama

v0.34.0

Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS. This release also improves structured output performance on Apple Silicon, adds support for OpenAI-compatible client tool search and response compaction, and makes images work correctly through compacted responses. Full Changelog: v0.33.3...v0.34.0-rc1

6 Sept github.com

ReleaseOllama

v0.33.3: gemma4: image and audio input support

Safetensors gemma4 imports served by the MLX engine now answer image and audio chats. Images run through both vision architectures: the transformer tower (26B, 31B, e-series) and the 12B's encoder-free unified embedder. Audio arrives through the same intake the ollama API already accepts for gemma4 GGUFs — WAV bytes in the images field, OpenAI input_audio parts, and /v1/audio/transcriptions uploads — with the e2b/e4b checkpoints running clips through their conformer audio encoder and the 12b unified checkpoint embedding the raw waveform directly. Clips longer than 30 seconds are split evenly into chunks of at most 30 seconds, cut at pauses, and encoded independently. Each modality serves only checkpoints that carry it: 26B/31B have no audio config and reject audio input, and checkpoints with an unrecognized vision architecture still load as text-only models and reject image requests. The server previously hid the vision and audio capabilities for gemma4 safetensors because the engine served neither. Both suppressions are removed, and existing imports start advertising the capabilities without re-importing since import already records them.

3 Sept github.com

ReleaseOllama

v0.33.0

What's Changed Claude Desktop Turn individual Ollama models on or off for use in Claude, directly from the menu bar Choose from your available Ollama models from within Claude; cloud models appear only when you're signed in A new Apps view manages app integrations with copyable commands Improved caching Fixed a hang where agent clients that cancel long prefills Prefill restore points are now trustworthy by construction: a cancelled prefill keeps every restore point it crossed, so retries resume where they stopped instead of restarting from scratch Resumed prefills no longer record restore points that fail to cover what they claim; on models with recurrent layers this previously forced a request matching 46k of 47k tokens to reprocess from zero Disabled Claude Code's "tokens left" token-countdown system message, which Ollama moved to the front of the prompt and broke the KV cache on every request Other improvements DeepSeek Harness launcher now falls back to npx when the global npm install fails, with Windows command-shim support Onboarding flow has clearer introductory copy, a macOS header aligned with the native traffic-light controls, and Cmd/Ctrl zoom shortcuts disabled during o…

26 Aug github.com

ReleaseOllama

v0.33.0

What's Changed Claude Desktop Turn individual Ollama models on or off for use in Claude, directly from the menu bar Choose from your available Ollama models from within Claude; cloud models appear only when you're signed in A new Apps view manages app integrations with copyable commands Improved caching Fixed a hang where agent clients that cancel long prefills Prefill restore points are now trustworthy by construction: a cancelled prefill keeps every restore point it crossed, so retries resume where they stopped instead of restarting from scratch Resumed prefills no longer record restore points that fail to cover what they claim; on models with recurrent layers this previously forced a request matching 46k of 47k tokens to reprocess from zero Disabled Claude Code's "tokens left" token-countdown system message, which Ollama moved to the front of the prompt and broke the KV cache on every request Other improvements DeepSeek Harness launcher now falls back to npx when the global npm install fails, with Windows command-shim support Onboarding flow has clearer introductory copy, a macOS header aligned with the native traffic-light controls, and Cmd/Ctrl zoom shortcuts disabled during o…

25 Aug github.com

ReleaseOllama

v0.33.0

What's Changed mlx: fix mac assumptions on linux/windows by @dhiltgen in #17898 mlx update by @dhiltgen in #17886 lint fixes by @dhiltgen in #17897 app: add claude desktop app by @ParthSareen in #17899 app: polish onboarding layout and disable zoom by @hoyyeva in #17885 launch: fall back to npx for DeepSeek Harness by @ParthSareen in #17758 mlxrunner: make prefix cache restore points survive cancelled and resumed prefills by @jessegross in #17901 app: add Connect your apps experience by @hoyyeva in #17900 app: claude model management by @ParthSareen in #17915 Full Changelog: v0.32.15...v0.33.0-rc0

22 Aug github.com

ReleaseOllama

v0.33.0

What's Changed mlx: fix mac assumptions on linux/windows by @dhiltgen in #17898 mlx update by @dhiltgen in #17886 lint fixes by @dhiltgen in #17897 app: add claude desktop app by @ParthSareen in #17899 app: polish onboarding layout and disable zoom by @hoyyeva in #17885 launch: fall back to npx for DeepSeek Harness by @ParthSareen in #17758 mlxrunner: make prefix cache restore points survive cancelled and resumed prefills by @jessegross in #17901 app: add Connect your apps experience by @hoyyeva in #17900 app: claude model management by @ParthSareen in #17915 Full Changelog: v0.32.15...v0.33.0-rc0

22 Aug github.com

ReleaseOllama

v0.33.0

What's Changed mlx: fix mac assumptions on linux/windows by @dhiltgen in #17898 mlx update by @dhiltgen in #17886 lint fixes by @dhiltgen in #17897 app: add claude desktop app by @ParthSareen in #17899 app: polish onboarding layout and disable zoom by @hoyyeva in #17885 launch: fall back to npx for DeepSeek Harness by @ParthSareen in #17758 mlxrunner: make prefix cache restore points survive cancelled and resumed prefills by @jessegross in #17901 app: add Connect your apps experience by @hoyyeva in #17900 app: claude model management by @ParthSareen in #17915 Full Changelog: v0.32.15...v0.33.0-rc0

22 Aug github.com

ReleaseOllama

v0.32.13: qwen3.8: support developer instructions (#17749)

qwen3.8: support developer instructions Qwen3.8 does not define a developer role, while OpenAI-compatible coding agents commonly send developer instructions before user messages. Fold the leading system/developer instruction prefix into a single system turn before Qwen3.8 validation, preserving instruction precedence without changing Qwen3.5 or other renderer behavior. Add streaming tool-call integration coverage for the native Ollama, OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages request shapes. Each case exercises prior assistant tool calls, tool results, follow-up rendering, and parsed tool-call output. Add Qwen3.8 to the release tools sweep. Removes an unnecessary unit test that should not have been included in the original 3.8 PR. review comments

14 Aug github.com

ReleaseOllama

v0.32.12: qwen3.8: add renderer and MLX import support

Qwen3.8 keeps the Qwen3.5 model architecture and parser, but its chat template adds reasoning-effort and preserved-thinking semantics. Detect those template markers during safetensors import, select the qwen3.8 renderer, and cover thinking, tools, continuation, and malformed parser input. Make indexed safetensors imports use the weight map's shard names instead of independently filtering files by the model-* convention. Reject unsafe shard paths, ignore unindexed tensors, and fail when an indexed weight is missing or stored in a different shard. Retain the conservative model-* scan when no index is present. Treat Classification.Quantize as the effective tensor format and pass it to the manifest writer. This records file_type for automatic block-FP8-to-MXFP8 conversion and recognized prequantized inputs, preserves requested quantization and base-plus-draft behavior, and avoids claiming one type for mixed or unknown formats. Normalize both supported convolution weight layouts with an explicit reshape.

14 Aug github.com

ReleaseOllama

v0.32.10

What's Changed Models that don't set a repeat_penalty now default to 1.0 (off) instead of 1.1, matching other engines and speeding up speculative decoding; set a per-model parameter if an older model repeats itself. Faster prefill on NVFP4 MLX models with a global scale, about 7–8% on Qwen3.6 and Muse Glimmer. Fixed blob verification being skipped when an OCI manifest's config and layer share a digest. New Contributors @vigneshakaviki made their first contribution in #15504 Full Changelog: v0.32.8...v0.32.10-rc1

13 Aug github.com

ReleaseOllama

v0.32.6

What's Changed Qwen3.5 is faster on Apple GPUs: the MLX engine now uses the model's MTP head for speculative decoding automatically /v1/chat/completions streaming now matches OpenAI's wire format: role only on the first chunk, finish_reason on its own chunk, and usage in a separate chunk with stream_options.include_usage. Truncated OpenAI responses now report finish_reason: "length" instead of "tool_calls". ollama run kimi-k3 now offers kimi-k3:cloud for cloud-only models that publish no default tag, instead of failing. TUI fixes: pipe-delimited prose no longer renders as a table, Enter accepts the highlighted @ file completion, and /prompt scrolling is no longer laggy. Experimental image generation has been temporarily removed. Continue using 0.32.5 for image generation support Updated the MLX and llama.cpp engines. Full Changelog: v0.32.5...v0.32.6-rc0

4 Aug github.com

ReleaseOllama

v0.32.4-rc0: model: add Laguna MLX support (#17237)

model: add Laguna MLX support Add Laguna XS 2, XS 2.1, and S 2.1 support to the MLX model and create paths. Read the source config to apply one quantization policy across dense and routed MoE layers. Keep the tied output head and router at source precision, quantize supported attention and expert projections, selectively promote sensitive expert down projections, and emit per-tensor metadata for mixed quantization blobs. Correct dense expert loading, BF16 source-layout handling, expert global-scale shapes and dtypes, routing-score scaling, and mixed-precision expert dispatch. Gate/up and down projections select quantized or dense execution independently so promoted BF16 down projections do not force quantized gate/up weights through the dense fallback. Optimize the forward pass with compatible gate/up fusion, sorted standard GatherMM and GatherQMM operations for larger prefills, model-local mlx.Compile closures for elementwise MoE work, and cache-backed 512-token prefill chunks. This keeps the implementation on maintained MLX operations without custom kernels.

25 Jul github.com

ReleaseOllama

v0.32.3

What's Changed Fixed model downloads that stall before sending data. Improved integrations: restored Claude Code Channels, fixed Anthropic thinking streams, and made Hermes Desktop respect --force-build. Expanded GPU support with CUDA on Windows ARM64, B200 support through CUDA 12, and lower memory use on Linux CUDA/ROCm iGPUs. Added chat, thinking, and tool calling support for Laguna 2.1 models, including a Metal inference fix. Fixed GLM tool calls being silently dropped at the end of generation. Updated the MLX and llama.cpp engines. Full Changelog: v0.32.1...v0.32.3

23 Jul github.com

← All news