cd/entity/Qwen3.6-35B-A3B-NVFP4· home› entities› Qwen3.6-35B-A3B-NVFP4
grep -l @qwen3.6-35b-a3b-nvfp4 /news/*.json | wc -l → 1

Qwen3.6-35B-A3B-NVFP4

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

10:37
2026-06-18
dev.to
large-language-models

Qwen3.6-35B NVFP4 runs on one H100 — A100 owners are out

NVIDIA released Qwen3.6-35B-A3B-NVFP4, a post-training FP4-quantized variant of Alibaba's 35B MoE model that fits on a single H100 by reducing VRAM from ~71 GB to ~23 GB. The quantization targets weig…

// co-occurs with top 7 entities
NVIDIA 1 Alibaba 1 H100 1 A100 1 Hopper 1 Blackwell 1 Model Optimizer 1