Qwen3-1.7B-GPTQ-Int8

Home/Models/Qwen/Qwen3-1.7B-GPTQ-Int8

Qwen/Qwen3-1.7B-GPTQ-Int8

kind: gptq
quant: gptq
family: qwen
modality: text-generation
root model: Qwen/Qwen3-1.7B
provider: Qwen
license: apache-2.0
language: —
context: 32,768
library: transformers
vRAM (GB): —
size on disk: —
downloads: 1,495
likes: 7
created: —
last modified: 2025-05-21T06:07:04+00:00 (2025)
huggingface: https://huggingface.co/Qwen/Qwen3-1.7B-GPTQ-Int8
tags: transformerssafetensorsqwen3text-generationconversationalarxiv:2505.09388base_model:Qwen/Qwen3-1.7Bbase_model:quantized:Qwen/Qwen3-1.7Blicense:apache-2.0text-generation-inferenceendpoints_compatible8-bitgptqregion:us

benchmark	category	score	context	conf	evidence
MMLU	knowledge	73.9		low	`\| Thinking \| bf16 \| 51.1 \| 40.1 \| 73.9 \|`
GPQA	reasoning	40.1		low	`\| Thinking \| bf16 \| 51.1 \| 40.1 \| 73.9 \|`

none scraped.