Coverage (30d)
4vs3
This Week
1vs1
Evidence
2 articlesRelationships
0Timeline
mlx-vlm2026-05-07
mlx-vlm v0.5.0 released with continuous batching, speculative decoding, and distributed inference for Apple Silicon
mlx-vlm2026-04-16
Next release to introduce continuous batching, OpenAI-compatible API, and vision caching.
mlx-vlm2026-04-04
Released version 0.4.4 with support for Falcon-Perception 300M and TurboQuant Metal kernels.
mlx-vlm2026-04-04
Achieved up to 1.9x faster decoding and 89% KV cache savings with TurboQuant Metal kernels.
mlx-vlm2026-03-29
Released version 0.4.2 with support for SAM3 and DOTS-MOCR models and critical fixes
Ecosystem
Apple Silicon
No mapped relationships
mlx-vlm
usesGemma 41 src
usesGemma41 src