Qwen3-235B-A22B-Thinking-2507-FP4-Eagle3

Home/Models/nvidia/Qwen3-235B-A22B-Thinking-2507-FP4-Eagle3

nvidia/Qwen3-235B-A22B-Thinking-2507-FP4-Eagle3

kind: original
quant: bf16 (16-bit)
family: qwen
modality: text-generation
root model: Qwen/Qwen3-235B-A22B-Thinking-2507-FP4
provider: nvidia
license: other
language: —
context: 262144
library: Model Optimizer
vRAM (GB): —
size on disk: —
downloads: 73
likes: 1
created: —
last modified: 2026-03-10T19:43:26+00:00 (2026)
huggingface: https://huggingface.co/nvidia/Qwen3-235B-A22B-Thinking-2507-FP4-Eagle3
tags: Model OptimizersafetensorsllamanvidiaModelOptQwen3-235B-A22B-Thinking-2507quantizedFP4Eagle3text-generationlicense:otherregion:us

benchmark	category	score	context	conf	evidence
MATH	math	3.15		medium	`\| math \| 3.15 \|`
MT-Bench	chat	2.13		low	`\| writing \| 2.13 \|`

none scraped.