vcruz305/MiniMax-M3.1-Flash-EXL3-Spark-recipe
MiniMax-M3.1-Flash EXL3 (SAGE 2.15 bpw) on ONE NVIDIA DGX Spark: pinned vLLM + vllm-exl3 recipe, q4 KV 32K, measured
GitHub repository with 6 stars and 0 forks.
Language: Shell
Topics: dgx-spark, exl3, exllamav3, gb10, minimax, vllm