minimax-m2.7-awq4-vllm

vllmtorch@official

MiniMax-M2.7-AWQ — AWQ quantized MiniMax M2.7

Quick Info

Runtimevllm (torch)

Tensor Parallel2

Nodes2+

Dtypeawq4

Containerghcr.io/spark-arena/dgx-vllm-eugr-nightly:latest

Tensor Parallel (--tp)GPU Memory (--gpu-mem)Port (--port)Served Model Name

sparkrun run @official/minimax-m2.7-awq4-vllm