Ollama releases
163 articles archived · Visit source ↗ · RSS
-
Ollama releases dev-tools 19h ago
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…
33 -
v0.40.4-rc2
launch: allow usage credits without upgrading ( #18985 )
23 -
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…
33 -
v0.40.3-rc0
server: skip local model compatibility migration ( #18908 )
7 -
v0.40.3
server: skip local model compatibility migration ( #18908 )
21 -
v0.40.2
Merge pull request #18855 from ollama/launch-claude-max-context-token…
36 -
v0.40.2
What's Changed README: add oxi to community integrations by @maziluiosif in #18739 server: hide duplicate and downgrade guards from list by @dhiltgen in #18874 New Contributors @maziluiosif made their first contribution in #18739 Full Changelog : v0.40.1...v0.40.2-rc0
28 -
v0.40.1-rc0
mlx: drop carried metal residency patch now that it is upstream ( #18854 )
37 -
v0.40.1
mlx: drop carried metal residency patch now that it is upstream ( #18854 )
32 -
v0.40.0
What's Changed Models run on MLX on Apple Silicon by default In this release, on Apple Silicon devices, model architectures supported by the MLX runtime will automatically run on MLX. ollama pull qwen3.8 ollama run qwen3.8 Additional models include gemma4 , qwen3.6 and qwen3.5…
9 -
v0.40.0
What's Changed Models run on MLX on Apple Silicon by default In this release, on Apple Silicon devices, model architectures supported by the MLX runtime will automatically run on MLX. ollama pull qwen3.8 ollama run qwen3.8 Additional models include gemma4 , qwen3.6 and qwen3.5…
23 -
v0.40.0-rc4: MLX: version bump (#18720)
MLX: version bump add scopes for unit tests to reduce memory usage
9 -
v0.40.0
What's Changed Models run on MLX on Apple Silicon by default In this release, on Apple Silicon devices, model architectures supported by the MLX runtime will automatically run on MLX. ollama pull qwen3.8 ollama run qwen3.8 Additional models include gemma4 , qwen3.6 and qwen3.5…
11 -
v0.40.0-rc2
Merge remote-tracking branch 'upstream/main' into release_v0.40.0
25 -
v0.35.0
Decision models Ollama now supports decision models through /v1/systemone , based on TypeSafe’s Jev API . Decision models return choices, probabilities, and scores instead of text. Use them for tasks such as ticket triage, model routing, and content classification. Available…
9 -
v0.35.0-rc1
mlx: bound pull stall retries and let the watchdog interrupt them ( #1 …
9 -
v0.34.4-rc1: mlxrunner: Update XGrammar to 0.2.7 for structured outputs
We pick up schema fixes for typed dictionary values and short arrays.
12 -
v0.34.4: mlxrunner: Update XGrammar to 0.2.7 for structured outputs
We pick up schema fixes for typed dictionary values and short arrays.
18 -
v0.34.3-rc1
server: allow registry cross-host redirects among allowlisted hosts (…
25 -
v0.34.3
server: allow registry cross-host redirects among allowlisted hosts (…
16 -
v0.34.3-rc0
api: expose model thinking levels and defaults ( #18473 )
35 -
v0.34.2
x/transfer, server: tighten redirect handling for registry requests (…
19 -
v0.34.2
What's Changed llama.cpp updates Full Changelog : v0.34.1...v0.34.2-rc0
19 -
v0.34.2
What's Changed llama.cpp updates Full Changelog : v0.34.1...v0.34.2-rc0
4 -
v0.34.1-rc1
mlx: add mlx patch to docker build context ( #18440 )
14 -
v0.34.1-rc0: MLX: version bump (#18235)
MLX: version bump mlx: support ModelOpt global scales in MoE models address comments address comments
19 -
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…
34 -
v0.34.0-rc5
openai: support standalone named function outputs ( #18348 )
12 -
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…
18 -
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…
33 -
v0.34.0-rc2
openai: finalize responses at the web search limit ( #18328 )
15 -
v0.34.0-rc1
app: harden Codex desktop proxy handling ( #18244 )
30 -
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…
22