Ollama releases
112 articles archived · Visit source ↗ · RSS
-
Ollama releases dev-tools 2d ago
v0.33.2-rc1
app: list account cloud models for Claude ( #18077 )
16 -
v0.33.1
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 loading models from slow storage New Contributors @pd95 made their first…
6 -
v0.33.1-rc1: linux: fix llama.cpp docker build (#18040)
Build context was missing the new cmake common utility.
29 -
v0.33.1-rc0: MLX: Qwen3.8 Flash Next support (#18032)
MLX: Qwen3.8 Flash Next support review comments
25 -
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…
6 -
v0.33.0
proxy: preserve string content during image fallback ( #18002 )
20 -
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…
4 -
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:…
20 -
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:…
31 -
v0.32.15-rc1: ci: plumb temporary MLX patch through to docker stages (#17874)
Follow up to #17850
35 -
v0.32.15-rc0: mlx update (#17850)
Temporarily carry ml-explore/mlx-c#127
28 -
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…
35 -
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…
14 -
v0.32.10
agent: allow multiple edits per edit tool call ( #17711 )
15 -
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…
5 -
v0.32.7
Muse Glimmer Note: Muse Glimmer is currently available via initial support via Ollama's MLX engine on Apple Silicon. Support for NVIDIA, AMD, and other platforms will be available in the coming days. Muse Glimmer , Meta's newest open model and the first released by Meta…
33 -
v0.32.5
What's Changed mlx update by @dhiltgen in #17397 Full Changelog : v0.32.4...v0.32.5-rc0
20 -
v0.32.4
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 on scheduler loaded map by @dhiltgen in #17376 qwen3_5: fix expert quantization…
37 -
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…
19 -
v0.32.3
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 llama.cpp by @dhiltgen in #17335 Full Changelog : v0.32.2...v0.32.3-rc0
9 -
v0.32.3
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 llama.cpp by @dhiltgen in #17335 Full Changelog : v0.32.2...v0.32.3-rc0
11 -
v0.32.2
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 @ParthSareen in #17228 agent: clean up semantics, UX, DX, and procedural code by…
24 -
v0.32.2: test: revamp integration test entrpoints (#16560)
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, while retaining the broad coverage in the library group.
25 -
v0.32.2
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 @ParthSareen in #17228 agent: clean up semantics, UX, DX, and procedural code by…
32 -
v0.32.2
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 @ParthSareen in #17228 agent: clean up semantics, UX, DX, and procedural code by…
31 -
v0.32.1
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 requests, and improved cache snapshot performance MLX text model loading now…
15 -
v0.32.1-rc0
cmd: put current working dir in the system prompt ( #17188 )
5 -
v0.32.0
launch: rename Codex App integration to ChatGPT ( #17161 )
25 -
v0.31.2-rc1: create: harden GGUF create flows (#17062)
create: harden GGUF create flows lint
26 -
v0.31.1: mlx: tighten up gemma4 moe loading code (#16964)
This change allows .experts.gate_proj / .up_proj / .down_proj tensor names to each be used for both quantized (i.e. nvfp4 and mxfp8) and non-quantized (bf16) models. Previous to this only non-quantized models used that tensor naming scheme.
20