HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/Qwen/Qwen/Qwen3-4B-Instruct-2507-FP8

Qwen/Qwen3-4B-Instruct-2507-FP8

family qwen · 1 variants · unknown

provider
Qwen
released
—
huggingface
https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507-FP8
best scores
MMLU-Pro: 62.8MMLU: 80.2GPQA: 50.3AIME 2025: 22.7LiveCodeBench: 31.5IFEval: 74.5Chatbot Arena: 15.9BFCL (function calling): 53.0

Best scores per benchmark

benchmarkcategorybest score
MMLUknowledge80.2
IFEvalinstruction-following74.5
MMLU-Proknowledge62.8
BFCL (function calling)agentic53.0
GPQAreasoning50.3
LiveCodeBenchcoding31.5
AIME 2025math22.7
Chatbot Arenachat15.9

Variants (1)

variantkindquantbitsvRAMdlorgyear
Qwen3-4B-Instruct-2507-FP8fp8fp88.096unsloth2025
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.