Qwen3-Next-80B-A3B-Instruct-bnb-4bit

Home/Models/unsloth/Qwen3-Next-80B-A3B-Instruct-bnb-4bit

unsloth/Qwen3-Next-80B-A3B-Instruct-bnb-4bit

kind: bnb-4bit
quant: 4bit
family: qwen
modality: text-generation
root model: Qwen/Qwen3-Next-80B-A3B-Instruct
provider: unsloth
license: apache-2.0
language: —
context: 262,144
library: transformers
vRAM (GB): —
size on disk: —
downloads: 908
likes: 27
created: —
last modified: 2025-09-13T09:58:35+00:00 (2025)
huggingface: https://huggingface.co/unsloth/Qwen3-Next-80B-A3B-Instruct-bnb-4bit
tags: transformerssafetensorsqwen3_nexttext-generationunslothconversationalarxiv:2309.00071arxiv:2404.06654arxiv:2505.09388arxiv:2501.15383base_model:Qwen/Qwen3-Next-80B-A3B-Instructbase_model:quantized:Qwen/Qwen3-Next-80B-A3B-Instructlicense:apache-2.0endpoints_compatible4-bitbitsandbytesregion:us

benchmark	category	score	context	conf	evidence
MMLU	knowledge	89.3	MMLU-Redux	medium	`\| MMLU-Redux \| 89.3 \| 85.7 \| 93.1 \| 90.9 \|`
IFEval	instruction-following	84.7	IFEval	medium	`\| IFEval \| 84.7 \| 83.2 \| 88.7 \| 87.6 \|`
MMLU-Pro	knowledge	78.4	MMLU-Pro	medium	`\| MMLU-Pro \| 78.4 \| 71.9 \| 83.0 \| 80.6 \|`
MMLU-Pro	knowledge	72.0	MMLU-ProX	medium	`\| MMLU-ProX \| 72.0 \| 69.3 \| 79.4 \| 76.7 \|`
GPQA	reasoning	70.4	GPQA	medium	`\| GPQA \| 70.4 \| 54.6 \| 77.5 \| 72.9 \|`
Chatbot Arena	chat	69.0	Arena-Hard v2*	medium	`\| Arena-Hard v2* \| 69.0 \| 34.1 \| 79.2 \| 82.7 \|`
BFCL (function calling)	agentic	65.1	BFCL-v3	medium	`\| BFCL-v3 \| 65.1 \| 63.0 \| 70.9 \| 70.3 \|`
AIME 2025	math	61.3	AIME25	medium	`\| AIME25 \| 61.3 \| 20.2 \| 70.3 \| 69.5 \|`
LiveCodeBench	coding	43.2	LiveCodeBench v6 (25.02-25.05)	medium	`\| LiveCodeBench v6 (25.02-25.05) \| 43.2 \| 29.1 \| 51.8 \| 56.6 \|`

none scraped.