What's Changed Improve ChatGPT CLI restore and graceful restart by @hoyyeva in #19583 cmd/launch: use thinking metadata for OpenCode settings by @hoyyeva in #19409…
What's Changed Improve ChatGPT CLI restore and graceful restart by @hoyyeva in #19583 cmd/launch: use thinking metadata for OpenCode settings by @hoyyeva in #19409…
Add the Ripple model, renderer, parser and import registration. Support per-layer NoPE in DFlash drafts. Fuse MLP activation, value blending and attention gating. …
What's Changed mlx: load bundled CUDA libraries in-process on Linux by @dhiltgen in #19433 model: add MiMo V2.6 model support by @dhiltgen in #19400 Full Changelog …
What's Changed mlx: load bundled CUDA libraries in-process on Linux by @dhiltgen in #19433 model: add MiMo V2.6 model support by @dhiltgen in #19400 Full Changelog …
What's Changed ci: pin buildx to workaround deadlock by @dhiltgen in #19373 openai: preserve readable Responses input content by @hoyyeva in #19192 mlx: sort long…
What's Changed ollama launch claude now applies the model's output token limit for Claude Code, so cloud models no longer run into the 128k default cap Cloud web…
LFM3 on Linux and Windows Liquid AI's LFM3 models, including text-to-speech in lfm3-audio and lfm3-omni , now run on Linux and Windows as well as Apple silicon. …
What's Changed llm: LFM3 GGUF fixes and llama-server speech by @dhiltgen in #19344 llama.cpp: version bump b11963 by @dhiltgen in #19360 Full Changelog …
Liquid AI LFM3 LFM3 is Liquid AI's new family of small models built for local agents, tool calling, and structured output, on Liquid's new tri-hybrid architecture. …
Liquid AI LFM3 LFM3 is Liquid AI's new family of small models built for local agents, tool calling, and structured output, on Liquid's new tri-hybrid architecture. …
What's Changed mlx: preserve small-image detail for compact Gemma 4 vision towers by @dhiltgen in #19247 MLX, MLX-C: version bump - prompt speed up for…
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…
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. …
NVIDIA Nemotron 3.5 Bolt E4B Nemotron 3.5 Bolt E4B is NVIDIA’s smaller, Gemma 4-based vision-language model for fast local conversations, image understanding, and…
flint: fix replies with thinking disabled Close the thinking section when think:false so Flint answers directly. Default and think:true prompts are unchanged. …
Ollama published release v0.40.9 on its official releases feed. The feed did not include notes, so this brief is the version and the primary source, nothing more.
Preserve source tool JSON alongside decoded API values so Flint can retain numeric types and schema order in prompts. Existing API marshaling is unchanged. …
Deduplicate MLX CUDA runtime payloads Move CUDA libraries shared by the GGML and MLX backends into the sibling CUDA payload, and teach in-process and subprocess MLX…
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…
What's Changed win: prevent orphaned runners by @dhiltgen in #18500 gguf: add the q2_0 tensor and file types by @jmorganca in #18967 Launch clef in Ollama's cloud by…
Behind a proxy, defer redirect-target DNS to the proxy; without one, keep the resolve-and-pin path. Trust default-registry/CDN hostnames with no local DNS. …
What's Changed win: prevent orphaned runners by @dhiltgen in #18500 gguf: add the q2_0 tensor and file types by @jmorganca in #18967 Launch clef in Ollama's cloud by…
ci: shorten Windows Vulkan build path Keep the nested shader-generator compiler probes below Windows path limits in checkouts with longer repository names. …
What's Changed mlx: port the Metal custom kernels to CUDA by @dhiltgen in #18657 docs: model recs and language standardization by @anra8571 in #18981 openai: accept…
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…
Decision models in the CLI Decision models can now be used directly from the terminal with ollama run — ask yes/no questions, classify text into labels, or score…
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…
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…
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…
Model upgrades Models downloaded with earlier versions of Ollama are upgraded in the background the first time you run them, for better performance and compatibility…
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…
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…
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…
Implements the EmbeddingGemma2Model architecture on the MLX runner: 24-layer bidirectional text encoder with PLE, shared gemma4 vision/audio towers, mean-pool + L2…
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…
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…
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…