Qwen2.5 14B Instruct › AMD Radeon 780M
Qwen2.5 14B Instruct on the AMD Radeon 780M
Best measured: 2.5 tokens/s generation and 78 tokens/s prompt processing (Q4_K_M, llamafile).
Every run
| Quant | Backend | Generate tok/s | Prompt tok/s | Test | Build / by / notes | Source |
|---|---|---|---|---|---|---|
| Q4_K_M | llamafile | 3.0 | 99 | LocalScore avg | LocalScore rank 191/418 | LocalScore (localscore.ai) |
| Q4_K_M | llamafile | 1.9 | 57 | LocalScore avg | LocalScore rank 258/418 | LocalScore (localscore.ai) |
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 780M · Qwen2.5 14B Instruct on other hardware