Qwen2.5 Coder 7B › NVIDIA DGX Spark (GB10)

Qwen2.5 Coder 7B on the NVIDIA DGX Spark (GB10)

Best measured: 29.4 tokens/s generation and 2,250 tokens/s prompt processing (Q8_0, CUDA, FA on).

Every run

Quant	Backend	Generate tok/s	Prompt tok/s	Test	Build / by / notes	Source
Q8_0	CUDA FA on	29.4	2,250	tg32	ggml-org maintainers Benchmarked repo: https://huggingface.co/ggml-org/Qwen2.5-Coder-7B-Q8_0-GGUF	llama.cpp benches/ (maintainer runs)

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 DGX Spark (GB10) · Qwen2.5 Coder 7B on other hardware