LLM Torrents
Models
Hardware
Log in
Qwen
Qwen2.5-VL-72B-Instruct — performance reports
Community-submitted & scraped throughput measurements. Sortable by generation speed.
← Back to model
Ran this model?
Log in
to submit your own performance result.
Filter by GPU / rig
Sort by
Generation tok/s (fastest first)
Prompt tok/s (fastest first)
Rig / GPU
Quant
Runtime
Context
Prompt tok/s
Gen tok/s
VRAM (GB)
Source
Reporter
No performance reports yet.