rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-E4B-MLX-8bit
Text Generation • 7B • Updated • 76
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
Raullen
updated 2
models 2 days ago
Raullen
published 2
models 2 days ago
Raullen
updated a
model 4 days ago
Raullen
published a
model 6 days ago
Possible MTP integration?
🔥 1
1
#1 opened 10 days ago
by 
koc-Z3
Raullen
updated 2
models 10 days ago
Raullen
published 2
models 10 days ago
Raullen
updated a
model 10 days ago
Raullen
published a
model 10 days ago
Raullen
updated a
model 10 days ago
Raullen
published a
model 10 days ago
Raullen
updated 4
models 12 days ago
rapid-mlx/Qwen3.8-Flash-Next-4bit
Text Generation • 76B • Updated • 1.08k • 5
rapid-mlx/Qwen3.8-27B-mixed-3.5bpw-MLX
Image-Text-to-Text • 27B • Updated • 855 • 8
rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX
Text Generation • 27B • Updated • 322
rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX
Text Generation • 27B • Updated • 1.23k • 3