Qwen2.5-72B-Instruct
1 workload result across 1 hardware configuration.
Fastest community-submitted config (not measured by llm-speed)
16.3 decode tok/s
on M3 Ultra (60-core GPU) + 96GB unified via mlx. see full run
Signed runs (1 workload result)
This run is community-submitted (signed on the submitter's own machine, not measured by llm-speed, and not used for llm-speed verdicts).
M3 Ultra (60-core GPU) + 96GB unified
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run | Source |
|---|---|---|---|---|---|---|---|
| chat-short | mlx@0.31.3 | 4BIT | 16.31tok/s | 23.25tok/s | 5,635ms | r_5c80gthqlh6 | Community-submitted |
Can Qwen2.5-72B-Instruct run on your hardware?
Fastest decode speed on each GPU or Mac, from llm-speed's own runs and community-submitted runs. Each page lists every quant and runtime and labels which runs llm-speed measured.
- M3 Ultra · 16.3 tok/s
Qwen2.5-72B-Instruct on hardware
Request a Qwen2.5-72B-Instruct run
No measured run yet for these pairs. Vote for the one you want; the most-requested runs go first. See all requests.
0 votes
We never sell or share your email. Privacy
llm-speed can measure this card · Submit your own
Compare Qwen2.5-72B-Instruct head-to-head
Check it for your setup
- Predict your exact setup: estimate whether Qwen2.5-72B-Instruct fits your GPU or Mac at your quant and context, next to measured speeds where we have them.
- Request this pair: ask for a measured Qwen2.5-72B-Instruct run on hardware we have not measured. Requests are ranked by votes.
- Full run table (1 run): every Qwen2.5-72B-Instruct result we have, with links to each source run.