Llama 2 7B › AMD Radeon RX 7900 XTX
Llama 2 7B on the AMD Radeon RX 7900 XTX
Best measured: 191 tokens/s generation and 3,890 tokens/s prompt processing (Q4_0, Vulkan, FA on).
Every run
| Quant | Backend | Generate tok/s | Prompt tok/s | Test | Build / by / notes | Source |
|---|---|---|---|---|---|---|
| Q4_0 | Vulkan FA on | 191 | 3,890 | tg128 | 304665f | llama.cpp Vulkan scoreboard (#10879) |
| Q4_0 | Vulkan FA off | 183 | 3,727 | tg128 | 304665f | llama.cpp Vulkan scoreboard (#10879) |
| Q4_0 | ROCm FA on | 170 | 3,874 | tg128 | 2f0c2db @Diablo-D3 | llama.cpp ROCm scoreboard (#15021) |
| Q4_0 | ROCm FA off | 167 | 3,552 | tg128 | 2f0c2db @Diablo-D3 | llama.cpp ROCm scoreboard (#15021) |
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.
No card yet?
Try it on a rented GPU (RunPod)Affiliate link: if you sign up, RigBench may earn a referral credit. It never affects rankings or numbers.
All results for the AMD Radeon RX 7900 XTX · Llama 2 7B on other hardware