O
v0.40.15
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: v0.40.14...v0.40.15-rc0
O
v0.40.14
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 search responses on /api/chat are now decoded correctly, including compressed responses OpenAI-compatible endpoints no longer override a model's packaged sampler defaults — clients that send no temperature/top_p get the model's own values…
O
v0.40.14-rc0
server: decode cloud web search responses (#19476)
O
v0.40.13
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. Full Changelog: v0.40.12...v0.40.13
O
v0.40.13-rc1: llama.cpp: workaround Metal unary crash (#19372)
This temporary patch works around a regression on older versions of MacOS ggml_metal_library_compile_all: failed to build 'unary' library
O
v0.40.13-rc0
llama.cpp: version bump b11963 (#19360)
O
v0.40.12
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. The family includes: lfm3: a 1.7B text model with a 256K-token context window lfm3-vl: adds image understanding lfm3-audio: speech recognition, translation, and text-to-speech in 18 languages lfm3-omni: text, images, and audio in one mo…
O
v0.40.12-rc1
mlx: add LFM3 and d1 models (#19333)
O
v0.40.12-rc0
llama.cpp: version bump b11901 (#19311)
O
v0.40.11
Speech Ollama can now generate speech on macOS. 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…
O
v0.40.9
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 w…
O
v0.40.11-rc0: voice: add voice catalog for Phonon (#19242)
mlxrunner: import and list Phonon catalog voices docs: document Phonon voices
O
v0.40.10
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 tool use. It supports a 128K-token context window. The model includes a DFlash draft for speculative decoding. ollama run nemotron-3.5-bolt:e4b Full Changelog: v0.40.9...v0.40.10
O
v0.40.10-rc0: 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 hea…
O
v0.40.9-rc3: Support GA Gradium Phonon checkpoints (#19227)
Replace the prerelease checkpoint path with Gradium's GA format, including default-voice import and speech conditioning. Set the 0.40.9 minimum, update the speech docs, and test import, inference setup, and rejection of the old checkpoint.
O
v0.40.9-rc2: flint: fix replies with thinking disabled (#19216)
flint: fix replies with thinking disabled Close the thinking section when think:false so Flint answers directly. Default and think:true prompts are unchanged. update template
O
v0.40.9-rc1
llama.cpp update (#19194)
O
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-expe…
O
v0.40.9-rc0: ci: switch to released WoA CTK (#19185)
We were still using a pre-release, and the download site is flaky, so lets get current on the latest CUDA Toolkit for WoA support.
O
v0.40.8-rc0: 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 M…
O
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…
O
v0.40.7-rc1: mlx: deduplicate CUDA runtime payloads (#17956)
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 loading to resolve that packaged dependency directory. Keep MLX-private libraries and JIT headers in the MLX overlay, include the full OpenBLAS Fortran runtime closure, and verify those dependencies in release packaging. address commen…
O
v0.40.7-rc0: mlx: add PPLX Decider v1.2 support (#19072)
Implement the Qwen3.5-backed decision scorer with noncausal attention, the publisher readout, image handling, and System One prompt encoding.
O
v0.40.6
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 @jberg5 in #19036 use identifiers for --ask mode question keys by @jberg5 in #19041 Full Changelog: v0.40.5...v0.40.6-rc0
O
v0.40.6-rc1: transfer: support proxies on registry redirect targets (#19065)
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. Fix a nil CancelFunc crash in blobDownload.release.
O
v0.40.6-rc0: Merge pull request #19041 from ollama/jberg/clef-question-ids
use identifiers for --ask mode question keys
O
v0.40.5
NVIDIA Nemotron 3.5 Super NVIDIA Nemotron 3.5 Super is a vision-language model for coding, reasoning, tool use, and document understanding. It pairs a 120B-parameter hybrid Mamba-2/Transformer mixture-of-experts backbone (12B active per token) with a C-RADIO vision encoder, and supports tool calling, an on/off thinking mode, and context up to 1M tokens. ollama run nemotron-3.5-super A compact sibl…
O
v0.40.5-rc2
llama.cpp: version bump b11669 (#19032)
O
v0.40.5-rc1: New model... (#19030)
ci: shorten Windows Vulkan build path Keep the nested shader-generator compiler probes below Windows path limits in checkouts with longer repository names. mlx: fix Nemotron bugs and support global scales Accept published Nemotron layer names while retaining legacy aliases, and fix layer-count inference and detached MTP quantization. Stabilize Mamba softplus, preserve FP32 vision normalization, an…
O
v0.40.5-rc0
MLX: version bump (#18993)