Qwen3.5-122B-A10B-NVFP4

Home/Models/nvidia/Qwen3.5-122B-A10B-NVFP4

nvidia/Qwen3.5-122B-A10B-NVFP4

kind: nvfp4
quant: nvfp4 (4-bit)
family: qwen
modality: text-generation
root model: Qwen/Qwen3.5-122B-A10B
provider: nvidia
license: apache-2.0
language: —
context: 262K
library: Model Optimizer
vRAM (GB): —
size on disk: —
downloads: 259,262
likes: 45
created: —
last modified: 2026-06-02T22:08:04+00:00 (2026)
huggingface: https://huggingface.co/nvidia/Qwen3.5-122B-A10B-NVFP4
tags: Model Optimizersafetensorsqwen3_5_moenvidiaModelOptQwen3.5quantizedNVFP4FP4nvfp4fp4text-generationconversationalbase_model:Qwen/Qwen3.5-122B-A10Bbase_model:quantized:Qwen/Qwen3.5-122B-A10Blicense:apache-2.08-bitmodeloptdeploy:azureregion:us

benchmark	category	score	conf	evidence
GPQA Diamond	reasoning	86.77	high	`\| NVFP4 \| 75.55 \| 86.77 \| 41.79 \| 67.13 \| 70.80 \|`
MMMU	multimodal	75.55	high	`\| NVFP4 \| 75.55 \| 86.77 \| 41.79 \| 67.13 \| 70.80 \|`
IFBench	instruction-following	70.8	high	`\| NVFP4 \| 75.55 \| 86.77 \| 41.79 \| 67.13 \| 70.80 \|`
SciCode	coding	41.79	high	`\| NVFP4 \| 75.55 \| 86.77 \| 41.79 \| 67.13 \| 70.80 \|`

none scraped.