Hugging Face's logo

majentik
/
Qwen3.5-27B-RotorQuant-MLX-2bit

Text Generation
MLX
Safetensors
English
qwen3_5
mlx-lm
rotorquant
2bit
quantized
kv-cache
qwen3.5
thinking
conversational
2-bit
Model card Files
xet
 Community
Qwen3.5-27B-RotorQuant-MLX-2bit / generation_config.json

Commit History

Add MLX 2-bit quantized Qwen3.5-27B with RotorQuant KV cache
a4d8e67
verified

majentik commited on