- v0.40.5 (2026-10-15)
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 s
- v0.40.5-rc2 (2026-10-15)
llama.cpp: version bump b11669 ( #19032 )
- v0.40.5-rc1: New model... (#19030) (2026-10-15)
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 f
- v0.40.5-rc0 (2026-10-14)
MLX: version bump ( #18993 )
- v0.40.4 (2026-10-14)
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 against a rubric: ollama run nimble --ask "Is a refund being requested?" < ticket.txt What's Changed Kev decision mode
- v0.40.4-rc2 (2026-10-13)
launch: allow usage credits without upgrading ( #18985 )
- v0.40.4-rc1: Add Kev decision scoring to MLX (#18976) (2026-10-13)
Add Kev decision scoring to MLX Load Kev models with their FP32 decision head and release metadata. Support System One scoring with shared-state caching and Kev-specific limits. address comments
- v0.40.4-rc0 (2026-10-12)
MLX, MLX-C: version bump ( #18956 )
- v0.40.3 (2026-10-11)
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 background model upgrade for embedding and other request performance, by @jmorganca in
- v0.40.3-rc0 (2026-10-09)
server: skip local model compatibility migration ( #18908 )