Llama 2 7B › AMD Ryzen AI Max+ 395 (Radeon 8060S)
Llama 2 7B on the AMD Ryzen AI Max+ 395 (Radeon 8060S)
Best measured: 54.4 tokens/s generation and 1,704 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 | 54.4 | 1,704 | tg128 | fb4b273 | llama.cpp Vulkan scoreboard (#10879) |
| Q4_0 | Vulkan FA off | 51.8 | 1,487 | tg128 | fb4b273 | llama.cpp Vulkan scoreboard (#10879) |
| Q4_0 | ROCm FA on | 49.9 | 1,004 | tg128 | e60f241 @firefox42 | llama.cpp ROCm scoreboard (#15021) |
| Q4_0 | ROCm FA on | 49.0 | 366 | tg128 | 1d0125b @hspak | llama.cpp ROCm scoreboard (#15021) |
| Q4_0 | ROCm FA off | 50.0 | 911 | tg128 | e60f241 @firefox42 | llama.cpp ROCm scoreboard (#15021) |
| Q4_0 | ROCm FA off | 48.0 | 351 | tg128 | 1d0125b @hspak | 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 Ryzen AI Max+ 395 (Radeon 8060S) · Llama 2 7B on other hardware