Llama 2 7B on the NVIDIA Tesla T4
Best measured: 46.4 tokens/s generation and 1,219 tokens/s prompt processing (Q4_0, CUDA, FA off).
Every run
| Quant | Backend | Generate tok/s | Prompt tok/s | Test | Build / by / notes | Source |
|---|---|---|---|---|---|---|
| Q4_0 | CUDA FA off | 46.4 | 1,219 | tg128 | d32e03f @pt13762104 | llama.cpp CUDA scoreboard (#15013) |
| Q4_0 | CUDA FA on | 44.0 | 1,310 | tg128 | d32e03f @pt13762104 | llama.cpp CUDA scoreboard (#15013) |
tg128 = generating 128 tokens; pp512 = reading a 512-token prompt (llama-bench). LocalScore averages several prompt and output lengths, so its numbers run lower than tg128.
Rent one by the hour
Rent a GPU on RunPodAffiliate link: if you sign up, RigBench may earn a referral credit. It never affects rankings or numbers.
All results for the NVIDIA Tesla T4 · Llama 2 7B on other hardware