Qwen3.6-35B-A3B-NVFP4-Fast

Home/Models/unsloth/Qwen3.6-35B-A3B-NVFP4-Fast

unsloth/Qwen3.6-35B-A3B-NVFP4-Fast

kind: nvfp4
quant: nvfp4 (4-bit)
family: qwen
modality: image-text-to-text
root model: Qwen/Qwen3.6-35B-A3B
provider: unsloth
license: apache-2.0
language: —
context: 262,144
library: transformers
vRAM (GB): —
size on disk: —
downloads: 317,401
likes: 89
created: —
last modified: 2026-07-12T13:48:21+00:00 (2026)
huggingface: https://huggingface.co/unsloth/Qwen3.6-35B-A3B-NVFP4-Fast
tags: transformerssafetensorsqwen3_5_moeimage-text-to-textunslothqwenqwen3_5conversationalbase_model:Qwen/Qwen3.6-35B-A3Bbase_model:quantized:Qwen/Qwen3.6-35B-A3Blicense:apache-2.0endpoints_compatible8-bitcompressed-tensorsregion:us

benchmark	category	score	conf	evidence
QuALITY	knowledge	100.0	medium	`quality=100`
AIME 2025	math	92.29	low	`\| Unsloth NVFP4 \| 85.85 \| 86.74 \| 92.29 \|`
GPQA	reasoning	86.74	low	`\| Unsloth NVFP4 \| 85.85 \| 86.74 \| 92.29 \|`
MMLU-Pro	knowledge	85.85	low	`\| Unsloth NVFP4 \| 85.85 \| 86.74 \| 92.29 \|`
Terminal-Bench	agentic-coding	2.0	medium	`Terminal-Bench 2.0`

none scraped.