Unverified50% confidenceReleaseExact time
Ollama v0.40.4 contains three changes directly related to MLX: state compaction after speculative rollback and an MLX / MLX-C version upgrade, both submitted by dhiltgen.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/14/2026
First Seen
Valid until: 10/28/2026
Sources
Related Entities
Related Claims
UnverifiedMLX 和 MLX-C 的版本升级直接影响 Ollama 在 Mac 上的推理性能、内存占用和模型兼容性。73% similarUnverifiedOllama v0.35.1 also updated the llama.cpp and MLX engines.69% similarUnverifiedOllama released the v0.40.4-rc1 pre-release, with the core change being the introduction of Kev decision scoring capability in the MLX backend.68% similarUnverifiedOllama released the v0.40.4 pre-release version, and this update includes inference engine upgrades, server-side routing optimizations, and improvements to MLX state management on the Apple Silicon platform.68% similarUnverifiedOllama v0.40.0 enabled support for models including gemma4, qwen3.8, qwen3.6, and qwen3.5 alongside MLX.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1030223API
curl https://kongchang.com/api/v1/knowledge/claims/1030223MCP
get_claim(id=1030223)