Qwen3-8B-AWQ

Home/Models/Qwen/Qwen3-8B-AWQ

Qwen/Qwen3-8B-AWQ

kind: awq
quant: awq
family: qwen
modality: text-generation
root model: Qwen/Qwen3-8B
provider: Qwen
license: apache-2.0
language: —
context: 32,768
library: transformers
vRAM (GB): —
size on disk: —
downloads: 824,569
likes: 52
created: —
last modified: 2025-05-21T06:09:42+00:00 (2025)
huggingface: https://huggingface.co/Qwen/Qwen3-8B-AWQ
tags: transformerssafetensorsqwen3text-generationconversationalarxiv:2309.00071arxiv:2505.09388base_model:Qwen/Qwen3-8Bbase_model:quantized:Qwen/Qwen3-8Blicense:apache-2.0text-generation-inferenceendpoints_compatible4-bitawqregion:us

benchmark	category	score	conf	evidence
MMLU	knowledge	87.5	low	`\| Thinking \| bf16 \| 67.1 \| 62.0 \| 87.5 \| 76.0 \|`
AIME 2024	math	76.0	low	`\| Thinking \| bf16 \| 67.1 \| 62.0 \| 87.5 \| 76.0 \|`
GPQA	reasoning	62.0	low	`\| Thinking \| bf16 \| 67.1 \| 62.0 \| 87.5 \| 76.0 \|`

none scraped.