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
Knowledge catalogue
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
What's Changed ollama launch claude no longer shows a warning about Claude connectors by @hoyyeva in #18878 ollama launch codex no longer warns about service tiers by @hoyyeva in #18879 Paused backgro
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 @h
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
When a legacy GGUF which requires our llama.cpp patch set is loaded, we do a lazy conversion on disk to make it llama.cpp compatible. To support downgrades, we temporarily hold both the new and old GG
Implements the EmbeddingGemma2Model architecture on the MLX runner: 24-layer bidirectional text encoder with PLE, shared gemma4 vision/audio towers, mean-pool + L2 output. /api/embed accepts per-item
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 qwen
mlx: match publisher tokenizer semantics Honor pretokenizer stage order, split behavior, Unicode boundaries, added-token normalization, and ranked BPE merges. Handle empty added tokens and empty Metas
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 su
What's Changed feat: allow ten web searches per response by @ParthSareen in #18602 MLX: version bump by @dhiltgen in #18651 llama.cpp: version bump b11232 by @dhiltgen in #18652 create: support explic
Add manifest-list storage so runner-specific manifests can coexist under one tag while preserving existing v1 tags as best-effort downgrade anchors. Show/list/copy/remove/pull/push now understand runn
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 Sys
What's Changed GET /api/show now advertises each model's thinking controls and default: curl http://localhost:11434/api/show -d '{'model': 'glm-5.3-flash:cloud'}' { 'thinking': { 'values': ['low', 'hi
What's Changed Added first-run setup when running ollama, with options to sign in or continue locally. Setup completion is shared with the desktop app on macOS and Windows. Added ollama://apps to open
The decode loop releases MLX's pool of freed buffers every 256 generated tokens, which is also how often the KV cache grows and drops its previous, smaller buffers. The check fires only when the token
model is one package with three jobs: the contract between the runner and the architectures, the opened checkpoint, and building nn layers from checkpoint tensors. Its files did not say which was whic
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 load
**Release Tag:** v0.34.2‑rc0 (commit `b10969`) **Key Details:** This release candidate bumps the version of *llama.cpp* and addresses a build issue where duplicate symbols were generated between `libl
**Release:** `v0.34.1‑rc0` (release candidate). **Repository:** `ollama/ollama`. **Key changes:** The release bumps the MLX library version, adds support for `ModelOpt` global scales in Mixture-of-Exp
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
Ollama released version v0.33.3 on September 2, 2024, based on commit 5ec5804 and signed with GitHub’s verified signature (GPG key B5690EEEBB952194). Key changes include default parameter definitions
What's Changed Ollama's app now follows the system appearance again, restoring dark mode support Fixed the macOS app to properly hand off to an already-running instance instead of starting a second on
What's Changed MLX: Qwen3.8 Flash Next support cmake: make external compat patches idempotent MLX and llama.cpp update mlxrunner: add structured output support mlxrunner: avoid Metal GPU timeouts when
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 #1789
**Release Summary – v0.32.15 (GitHub Release)** Version 0.32.15 was published on **19 Aug**, adding a *model metadata cache* to reduce per‑request overhead in Ollama. The release builds on the previou
Ollama released pre‑release **v0.32.14 rc0** (commit d67ad83, GPG key B5690EEEBB952194) on 15 Aug at 19:41. Notable changes include WebP image transcoding for the llama‑server renderer and allowing Qw
What's Changed launch: add Muse Code integration by @dhiltgen in #17594 model/renderers: match Muse Glimmer reasoning template by @dhiltgen in #17732 launch: add DeepSeek Harness integration by @Parth
Qwen 3.8 - 27B model support This release adds the support of Qwen 3.8 27B. For Apple Silicon devices, Ollama has in particular optimized for maximum performance and output quality suitable for repeat
**Ollama v0.32.13 Release (14 Aug)** The release contains a single signed commit (ID 0f25c31) verified with GitHub’s GPG key B5690EEEBB952194. The primary change in this version is the addition of dev
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
ModelOpt checkpoints apply a float32 global scale to every projection output on top of the per-group quantization scales. Running the multiply and the cast back to the activation dtype as separate eag
Muse Glimmer Muse Glimmer is now available on all platforms. Muse Glimmer can power coding agent applications such as Claude Code, Codex, Pi and more, as well as long-running personal assistants such
NVIDIA Nemotron 3.5 Lightning NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents. It is designed f
Muse Glimmer Note: Muse Glimmer is currently available via initial support via Ollama's MLX engine on Apple Silicon. Additional support and optimizations for Apple Silicon, NVIDIA, AMD, and other plat
v0.32.8 is an Oct 10, 2023 release of the ollama repository on GitHub, following a pre‑release tag v0.32.8‑rc0. The update adds Muse Glimmer support for NVIDIA, AMD and additional platforms, with the
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: rol
**Ollama – v0.32.5 Release Summary** - Version **v0.32.5** (released 27 Jul at 01:25) is the latest stable release on GitHub, with a signed commit (GPG Key ID B5690EEEBB952194). - The update includes
What's Changed x/create: quantize lm_head at 8-bit in the requested family by @jessegross in #17357 test: harden flaky updater and transfer unit tests by @dhiltgen in #17378 server: fix ps data race o
What's Changed mlx update by @dhiltgen in #17332 model/parsers: finalize incomplete GLM tool calls by @dhiltgen in #17250 docs: update retirements by @mxyng in #17289 model: align Laguna with upstream
What's Changed launch: keep Claude Code channels available by @hoyyeva in #17210 cmd: remove dead agent prompt wrappers by @ParthSareen in #17227 agent: reorder working directory instruction by @Parth
The **v0.32.2‑rc1** release (commit 4d1b53e, signed with a GPG key) introduces server-side logic to detect download stalls that occur before any data is received. It also removes the stall‑timeout set
This refactors the existing integration tests into 3 priumary groups: fast, release, and library. It also refines some of the release tests to drop some of the older models and pick up newer models, w
**Release v0.32.2‑rc0 (commit de1ce45)** adds support for Compute Capability 10.0 in the Linux “CUDA v12” preset, enabling B200‑class GPUs to use the `cuda_v12` backend even when drivers do not meet t
What's Changed Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations Fixed a recurrent MLX model cache leak that could increase memory use across
What's Changed New interactive agent experience: running ollama now launches an agent to help you code and delegate work ❯ ollama Ollama 0.32.0 ▸ Chat, Code, & Work (glm-5.2:cloud) Chat with models, c
The search results do not contain specific information about v0.32.0-rc0. Based on the version numbering and context from Ollama's release patterns, v0.32.0-rc0 is a release candidate for Ollama, a la
Ollama v0.31.2-rc1 is a pre-release version released on July 6, 2026. This release includes CI improvements to avoid unbounded parallelism, fixes for CUDA toolkit lookup, updates to cloud documentatio
This release candidate introduces support for offloading the image GPU projection (mmproj) to an integrated GPU when using fit padding in Ollama's LLM processing, addressing technical improvements for
v0.31.2-rc0 is a release candidate for Ollama that removes the OLLAMA_EXPERIMENT=client2 experimental flag and updates the MLX engine to the latest version . The release includes contributions from mu
v0.30.12 is a release candidate (rc0) that fixes a gemma4:12b floating point exception crash on x86, CUDA, Linux, and Windows systems. It includes improvements to ollama launch for Hermes Desktop, all
Ollama v0.30.11 is a release candidate from the v0.30 series (June 2026) , which pairs the new MLX engine on Apple Silicon with continued llama.cpp improvements for enhanced compatibility across Mac a
Ollama v0.30.7 is a pre-release update that includes documentation improvements and native Windows Hermes config path support . This release contains updates to Zod example documentation to use native
v0.30.7-rc1 is a release candidate for Ollama, an open-source platform for running and managing large language models locally. The v0.30 series represents improved compatibility and performance using
Ollama v0.30.6 fixes SSE streaming by skipping idle comment frames in completion and chat requests, addressing an issue where llama.cpp's default 30-second SSE ping caused streaming problems. The rele
v0.30.6-rc0 is a release candidate that fixes kernel template instantiation so library symbols are exported correctly , following improvements from the v0.30 series. The v0.30 base release improved co
v0.30.5 is a release candidate version of Ollama, a local large language model runner. The v0.30 series features improved compatibility and performance using llama.cpp and augments the MLX engine on A
Ollama v0.30.2 is a patch release from the 0.30 series, which features improved compatibility and performance using llama.cpp, augmented MLX engine support on Apple Silicon, and broader model support
Ollama v0.30.3 adds support for the Gemma 4-12B model . This is a minor patch release that builds on the v0.30 series, which provides improved compatibility and performance improvements. The release w
Ollama v0.30.4 is a patch release within the v0.30 series, which offers improved compatibility and performance using llama.cpp, augments the MLX engine on Apple Silicon with wider hardware support, an
Ollama v0.30.4 is a patch release addressing a bug in the llama-server component related to incorrect parameter wiring in the Gemma 4 model implementation. This fix ensures Gemma 4 models operate corr