Unverified50% confidenceFactExact time
Change #19291 bumps the version numbers of both MLX and MLX-C, officially described as improving prompt processing speed for the gemma, flint and laguna model families.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/27/2026
First Seen
Valid until: 1/25/2027
Sources
Related Entities
Related Claims
UnverifiedOllama 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.71% similarUnverifiedAfter MLX is enabled by default, supported models may have advantages in inference speed and memory utilization, but the official team has not released unified performance data.67% similarUnverifiedMLX 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。66% similarUnverifiedAfter adding speculative decoding to the MLX inference backend, reply speed on Mac is up to 2.8x faster with identical output, and draft depth is set automatically, supporting multiple draft models such as MTP, DFlash, DSpark and EAGLE-3.65% similarUnverifiedDecision-class models such as Nimble, tev1, clef, and clef-flash have begun to offer support on MLX.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1101755API
curl https://kongchang.com/api/v1/knowledge/claims/1101755MCP
get_claim(id=1101755)