Qwen2.5-7B-Instruct
8 workload results across 3 hardware configurations.
Fastest community-submitted config (not measured by llm-speed)
246.7 decode tok/s
on RTX 5090 (32GB) via llama.cpp. see full run
Signed runs (8 workload results)
All 5 runs are community-submitted (signed on the submitter's own machine, not measured by llm-speed, and not used for llm-speed verdicts).
RTX 5090 (32GB)
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run | Source |
|---|---|---|---|---|---|---|---|
| chat-short | llama.cpp | - | 232.7tok/s | no data | 37.0ms | r_1shiviswt3d | Community-submitted |
| chat-long | llama.cpp | - | 232.4tok/s | no data | 239ms | r_1shiviswt3d | Community-submitted |
| concurrent-decode | llama.cpp | - | 240.7tok/s | no data | no data | r_1shiviswt3d | Community-submitted |
| agent-trace | llama.cpp | - | 232.5tok/s | 38,007.7tok/s | 57.1ms | r_1shiviswt3d | Community-submitted |
| chat-short | llama.cpp | - | 246.7tok/s | no data | 33.9ms | r_3yn-4321hp- | Community-submitted |
M3 Pro (18-core GPU) + 36GB unified
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run | Source |
|---|---|---|---|---|---|---|---|
| chat-short | mlx@0.31.3 | 4BIT | 30.52tok/s | 161.9tok/s | 809ms | r_llzv_g-ymaf | Community-submitted |
| chat-short | mlx@0.31.3 | 4BIT | 15.67tok/s | 54.34tok/s | 2,411ms | r_e3t93rscswq | Community-submitted |
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 | 139.6tok/s | 190.0tok/s | 689ms | r_5r6rhiynenc | Community-submitted |
Can Qwen2.5-7B-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.
Qwen2.5-7B-Instruct on hardware
Request a Qwen2.5-7B-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 Qwen2.5-7B-Instruct head-to-head
Check it for your setup
- Predict your exact setup: estimate whether Qwen2.5-7B-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 Qwen2.5-7B-Instruct run on hardware we have not measured. Requests are ranked by votes.
- Full run table (5 runs): every Qwen2.5-7B-Instruct result we have, with links to each source run.