HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Qwen3-4B-AWQ

Qwen/Qwen3-4B-AWQ

kind
awq
quant
awq
family
qwen
modality
text-generation
root model
Qwen/Qwen3-4B
provider
Qwen
license
apache-2.0
language
—
context
32,768
library
transformers
vRAM (GB)
—
size on disk
—
downloads
586,745
likes
31
created
—
last modified
2025-05-21T06:13:28+00:00 (2025)
huggingface
https://huggingface.co/Qwen/Qwen3-4B-AWQ
tags
transformerssafetensorsqwen3text-generationconversationalarxiv:2309.00071arxiv:2505.09388base_model:Qwen/Qwen3-4Bbase_model:quantized:Qwen/Qwen3-4Blicense:apache-2.0text-generation-inferenceendpoints_compatible4-bitawqregion:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
MMLUknowledge83.7low| Thinking | bf16 | 63.6 | 55.9 | 83.7 | 73.8 |
AIME 2024math73.8low| Thinking | bf16 | 63.6 | 55.9 | 83.7 | 73.8 |
GPQAreasoning55.9low| Thinking | bf16 | 63.6 | 55.9 | 83.7 | 73.8 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.