Qwen3.6-35B-A3B-NVFP4

Home/Models/nvidia/Qwen3.6-35B-A3B-NVFP4

nvidia/Qwen3.6-35B-A3B-NVFP4

kind: nvfp4
quant: nvfp4 (4-bit)
family: qwen
modality: text-generation
root model: Qwen/Qwen3.6-35B-A3B
provider: nvidia
license: apache-2.0
language: —
context: 262K
library: Model Optimizer
vRAM (GB): —
size on disk: —
downloads: 9,864,413
likes: 507
created: —
last modified: 2026-06-12T21:32:12+00:00 (2026)
huggingface: https://huggingface.co/nvidia/Qwen3.6-35B-A3B-NVFP4
tags: Model Optimizersafetensorsqwen3_5_moenvidiaModelOptQwen3.6quantizedFP4fp4text-generationconversationalbase_model:Qwen/Qwen3.6-35B-A3Bbase_model:quantized:Qwen/Qwen3.6-35B-A3Blicense:apache-2.08-bitmodeloptdeploy:azureregion:us

no scores extracted for this variant.

title	author	status	type
why can not quit with ctrl-c when run with vllm 0.24.0 in jetson agx orin 64G, and MTP generate gibberish	loveyoupeng	open	disc
别开MTP，开了变傻逼	jiecong	open	disc
Multi-GPU NVFP4 issues on 16 GB cards (RTX 4060 Ti)	Josephur	open	disc
TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecture	vigneshwar234	open	disc
DGX Spark is not running qwen3.6 35b a3b nvfp4 on nvidia vllm image	moranilt	open	disc
[Bug] Three stability failure modes on RTX 5090 (consumer Blackwell, SM120) — illegal instruction, CUDA-graph-replay crash, and silent engine hang	YoRandom	open	disc
Bazaar: Monetize your Text-to-Speech Model as a pay-per-query API	gionuibk	open	disc
Bazaar: Monetize your Text-to-Speech Model as a pay-per-query API	gionuibk	open	disc
Qwen3.6-27B-NVFP4?	YanTianlong	closed	disc
Genuinely a fantastic model	swtb	open	disc
RTX 5090 performence	jasionkajakub	open	disc
Benchmark Report: Qwen3.6-35B-A3B-NVFP4 on NVIDIA DGX Spark, Jetson Thor, Blackwell 6000 Pro	shakhizat	open	disc
NVIDIA GeForce RTX 5090	Mosai-Sys	open	disc
on the DGX spark	shakhizat	open	disc