Qwen3-Next-80B-A3B-Thinking-FP8

Home/Models/Qwen/Qwen3-Next-80B-A3B-Thinking-FP8

Qwen/Qwen3-Next-80B-A3B-Thinking-FP8

kind: fp8
quant: fp8 (8-bit)
family: qwen
modality: text-generation
root model: Qwen/Qwen3-Next-80B-A3B-Thinking
provider: Qwen
license: apache-2.0
language: —
context: 262,144
library: transformers
vRAM (GB): —
size on disk: —
downloads: 24,453
likes: 54
created: —
last modified: 2025-09-22T05:39:57+00:00 (2025)
huggingface: https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking-FP8
tags: transformerssafetensorsqwen3_nexttext-generationconversationalarxiv:2309.00071arxiv:2505.09388arxiv:2501.15383base_model:Qwen/Qwen3-Next-80B-A3B-Thinkingbase_model:quantized:Qwen/Qwen3-Next-80B-A3B-Thinkinglicense:apache-2.0endpoints_compatiblefp8deploy:azureregion:us

benchmark	category	score	context	conf	evidence
MMLU	knowledge	91.4	MMLU-Redux	medium	`\| MMLU-Redux \| 91.4 \| 90.9 \| 93.8 \| 92.1 \| 92.5 \|`
IFEval	instruction-following	88.9	IFEval	medium	`\| IFEval \| 88.9 \| 85.0 \| 87.8 \| 89.8 \| 88.9 \|`
AIME 2025	math	85.0	AIME25	medium	`\| AIME25 \| 85.0 \| 72.9 \| 92.3 \| 72.0 \| 87.8 \|`
MMLU-Pro	knowledge	80.9	MMLU-Pro	medium	`\| MMLU-Pro \| 80.9 \| 79.1 \| 84.4 \| 81.9 \| 82.7 \|`
MMLU-Pro	knowledge	76.4	MMLU-ProX	medium	`\| MMLU-ProX \| 76.4 \| 74.6 \| 81.0 \| 80.2 \| 78.7 \|`
GPQA	reasoning	73.4	GPQA	medium	`\| GPQA \| 73.4 \| 68.4 \| 81.1 \| 82.8 \| 77.2 \|`
BFCL (function calling)	agentic	72.4	BFCL-v3	medium	`\| BFCL-v3 \| 72.4 \| 70.3 \| 71.9 \| 68.6 \| 72.0 \|`
LiveCodeBench	coding	66.0	LiveCodeBench v6 (25.02-25.05)	medium	`\| LiveCodeBench v6 (25.02-25.05) \| 66.0 \| 60.6 \| 74.1 \| 61.2 \| 68.7 \|`
Chatbot Arena	chat	56.0	Arena-Hard v2*	medium	`\| Arena-Hard v2* \| 56.0 \| 48.4 \| 79.7 \| 56.7 \| 62.3 \|`

none scraped.