Qwen3-30B-A3B-GPTQ-Int4

Home/Models/Qwen/Qwen3-30B-A3B-GPTQ-Int4

Qwen/Qwen3-30B-A3B-GPTQ-Int4

kind: gptq
quant: gptq
family: qwen
modality: text-generation
root model: Qwen/Qwen3-30B-A3B
provider: Qwen
license: apache-2.0
language: —
context: 32,768
library: transformers
vRAM (GB): —
size on disk: —
downloads: 147,555
likes: 54
created: —
last modified: 2025-05-21T06:08:09+00:00 (2025)
huggingface: https://huggingface.co/Qwen/Qwen3-30B-A3B-GPTQ-Int4
tags: transformerssafetensorsqwen3_moetext-generationconversationalarxiv:2309.00071arxiv:2505.09388base_model:Qwen/Qwen3-30B-A3Bbase_model:quantized:Qwen/Qwen3-30B-A3Blicense:apache-2.0endpoints_compatible4-bitgptqregion:us

benchmark	category	score	conf	evidence
MMLU	knowledge	89.5	low	`\| Thinking \| bf16 \| 74.3 \| 65.8 \| 89.5 \| 80.4 \|`
AIME 2024	math	80.4	low	`\| Thinking \| bf16 \| 74.3 \| 65.8 \| 89.5 \| 80.4 \|`
GPQA	reasoning	65.8	low	`\| Thinking \| bf16 \| 74.3 \| 65.8 \| 89.5 \| 80.4 \|`

none scraped.