Qwen2.5 VL 72B Instruct

Qwen · released 2025-02-01 · other license

Qwen2.5 VL 72B Instruct by Qwen — 73.41B open-weight local LLM. License: other. Benchmarks, VRAM requirements per quantization, GPU compatibility, pricing and community reviews on robotanalyze.com.

Key specs

TypeLocal open-weight
Parameters73.41B total
Architectureqwen2_5_vl
Context window131K tokens
Knowledge cutoff2024-06-30
Modalitiestext, vision
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond
SWE-bench Verified
AIME
MMLU-Pro
BFCL v3 (tool use)
Composite score
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M44.1 GB42.6 GB131K