AI & ML interests

Open-source OpenAI- and Anthropic-compatible LLM runtime for Apple Silicon. Up to 4× faster than mlx-lm, same weights. Reliable tool calling for coding agents.

Recent Activity

Raullen  updated a model about 7 hours ago
rapid-mlx/Qwen3.8-Flash-Next-4bit
Raullen  updated a model about 7 hours ago
rapid-mlx/Qwen3.8-27B-mixed-3.5bpw-MLX
Raullen  updated a model about 7 hours ago
rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX
View all activity

rapid-mlx 's datasets

None public yet