Qwen2.5 14B Instruct on the NVIDIA L40S-8Q

Best measured: 3.5 tokens/s generation and 343 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	3.5	343	LocalScore avg	LocalScore rank 144/418; 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.

Check prices

Amazon Newegg

As an Amazon Associate I earn from qualifying purchases.

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 RunPod

Affiliate link: if you sign up, RigBench may earn a referral credit. It never affects rankings or numbers.

All results for the NVIDIA L40S-8Q · Qwen2.5 14B Instruct on other hardware