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
View all activity
Organization Card
Welcome to your static Space!
You can modify this app directly by editing index.html in the Files and versions tab.
Also don't forget to check the Spaces documentation.
models 10
rapid-mlx/Qwen3.8-Flash-Next-4bit
Text Generation • 76B • Updated • 638 • 1
rapid-mlx/Qwen3.8-27B-mixed-3.5bpw-MLX
Image-Text-to-Text • 27B • Updated • 838 • 7
rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX
Text Generation • 27B • Updated • 358
rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX
Text Generation • 27B • Updated • 790 • 2
rapid-mlx/NeoHorse-1-9B-MLX-4bit
Text Generation • 9B • Updated • 289 • 1
rapid-mlx/Ling-3.0-tiny-MLX-4bit
Text Generation • 8B • Updated • 84.2k • 6
rapid-mlx/GLM-5.3-Flash-MTP-4bit
7B • Updated • 795
rapid-mlx/G9v3-39A5B-MLX-4bit
Text Generation • 39B • Updated • 109
rapid-mlx/DeepSeek-V4.1-Flash-REAP-2bit-MLX
Text Generation • 681B • Updated • 3.41k • 1
rapid-mlx/DeepSeek-V4.1-Flash-DSpark-4d2e-MLX
7B • Updated • 2.59k • 2
datasets 0
None public yet