Qwen2.5 14B Instruct › NVIDIA RTX PRO 2000 Blackwell Laptop
Qwen2.5 14B Instruct on the NVIDIA RTX PRO 2000 Blackwell Laptop
Best measured: 2.1 tokens/s generation and 230 tokens/s prompt processing (Q4_K_M, llamafile).
For comparison, our size-scaling estimate for this combination is 22.1 tok/s.
Every run
| Quant | Backend | Generate tok/s | Prompt tok/s | Test | Build / by / notes | Source |
|---|---|---|---|---|---|---|
| Q4_K_M | llamafile | 2.1 | 230 | LocalScore avg | LocalScore rank 181/418; model file is larger than this card's VRAM, so part of it ran on the CPU/system RAM | 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.
Doesn't fit in this card's VRAM
Part of this model ran on the CPU here. A rented 48-80 GB GPU keeps it all in VRAM.
Rent a bigger 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 RTX PRO 2000 Blackwell Laptop · Qwen2.5 14B Instruct on other hardware