Avg Speed1002.71 t/s
Latency0.82 s
Total Tests25
Models5
Updated3/14/2026
Created At3/13/2026
F
Futureppo
A non-profit API provider offering access to various AI models including Codex, Claude Code, and Open Code through multiple endpoints.
Community
Join LMSpeed QQ Group
Join us for speed-test updates and support. Group ID:
A non-profit API provider offering access to various AI models including Codex, Claude Code, and Open Code through multiple endpoints.
| Model | Speed | Latency | Tests |
|---|---|---|---|
| llama3.1-8b | 2301.73 t/s | 0.38s | 10 |
| nvidia/nemotron-3-nano-30b-a3b | 257.88 t/s | 0.74s | 5 |
| qwen/qwen3-next-80b-a3b-instruct | 115.65 t/s | 0.55s | 5 |
| qwen/qwen3-next-80b-a3b-instruct | 115.65 t/s | 0.55s | 5 |
| nvidia/llama-3.1-nemotron-nano-vl-8b-v1 | 36.57 t/s | 2.05s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Mar 13, 09:19 PM | llama3.1-8b | 2376.41 t/s | 0.38s |
| Mar 13, 09:09 PM | llama3.1-8b | 2227.05 t/s | 0.39s |
| Mar 13, 09:03 PM | nvidia/llama-3.1-nemotron-nano-vl-8b-v1 | 36.57 t/s | 2.05s |
| Mar 13, 09:01 PM | qwen/qwen3-next-80b-a3b-instruct | 115.65 t/s | 0.55s |
| Mar 13, 09:00 PM | nvidia/nemotron-3-nano-30b-a3b | 257.88 t/s | 0.74s |