MiniMax-M2.7 AWQ 4bit (W4A16)

• Format: compressed-tensors pack-quantized, int4 weights / fp16 activations
• Group size: 128, symmetric
• Calibration: data-free, MSE observer
• Kept in BF16: MoE routing gates and lm_head only — every other Linear is quantized, matching the ignore list from cyankiwi/MiniMax-M2.5-AWQ-4bit.

vLLM

vllm serve demon-zombie/MiniMax-M2.7-AWQ-4bit \
  --tensor-parallel-size 4 \
  --tool-call-parser minimax_m2 \
  --reasoning-parser minimax_m2 \
  --enable-auto-tool-choice