RavenX MLX Models — Apple Silicon Inference Stack
Collection
TurboQuant 4-bit mlx-lm models. TriAttention compatible. PR #1 merged MIT+NVIDIA. • 9 items • Updated • 1
Rayhan
shuvrobhai
·
AI & ML interests
None yet
Recent Activity
liked a model about 2 months ago
majentik/gemma-4-E2B-TurboQuant-MLX-2bit upvoted a collection about 2 months ago
RavenX MLX Models — Apple Silicon Inference Stack upvoted a collection 2 months ago
💧 LFM2.5Organizations
None yet
upvoted a collection about 2 months ago