Laguna-S-2.1-ModelOpt-NVFP4-W4A4-vllm
A 64.38 GiB NVFP4 quantization of poolside/Laguna-S-2.1 (117.6 B params) that serves on a single DGX Spark (GB10,...
Метка: w4a4
DeepSeek-V4-Flash-NVFP4-TP2-W4A4-v1
This is a single-download, two-node GB10 serving bundle. It combines an offline-prepared NVIDIA NVFP4 W4A4 target with the...
llm-jp-4-32b-a3b-thinking-NVFP4
Квантование NVFP4 (W4A4) модели мышления (рассуждения) llm-jp/llm-jp-4-32b-a3b-thinking — японской модели мышления (рассуждения) Mixture-of-Experts с 32B-A3B битами. Квантовано с...
m51Lab-MiniMax-M2.7-REAP-139B-A10B-NVFP4-GB10
What happened: The initial upload (2026-04-15) used ignore=[«lmhead»] in the llm-compressor recipe, which meant the 62 MoE routers...