Llama 2 7B on the Nvidia Tesla T10

Best measured: 76.0 tokens/s generation and 1,840 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	76.0	1,840	tg128	7f76692 coopmat2	llama.cpp Vulkan scoreboard (#10879)
Q4_0	Vulkan FA off	75.0	1,693	tg128	7f76692 coopmat2	llama.cpp Vulkan scoreboard (#10879)

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.

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 Nvidia Tesla T10 · Llama 2 7B on other hardware