Qwen2.5 72B Instruct

Qwen · released 2024-09-19 · other license

Qwen2.5-72B-Instruct is Alibaba's flagship 2024 open-weight non-reasoning model: vendor GPQA 49.0, MMLU-Pro 71.1, LiveCodeBench 55.5. A leading open model of its time.

Key specs

TypeLocal open-weight
Parameters72.71B total
Architectureqwen2
Context window131K tokens
Knowledge cutoff2024-06-30
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond49%
SWE-bench Verified
AIME
MMLU-Pro71.1%
BFCL v3 (tool use)
Composite score6.67
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M43.7 GB42.2 GB131K

Strengths & weaknesses

Strengths: Strong math and reasoning (vendor MATH 83.1); Leading multilingual instruction following; Top open intelligence in its 2024 size class

Weaknesses: No native reasoning mode; Restrictive (non-Apache) Qwen license at 72B