RadixArk/Qwen3.8-2.4T-A95B-NVFP4
Text Generation • 1.3T • Updated • 6.96k • 4
Qwen3.8
Qwen3.8 in NVFP4 (W4A4) — production checkpoints plus DSpark drafts for speculative decoding, built for SGLang. Recipes: https://cookbook.sglang.ai
Qwen3.8 in NVFP4 (W4A4) — production checkpoints plus DSpark drafts for speculative decoding, built for SGLang. Recipes: https://cookbook.sglang.ai