GLM-4.7-Flash on the NVIDIA DGX Spark (GB10)

Best measured: 48.7 tokens/s generation and 2,364 tokens/s prompt processing (Q8_0, CUDA, FA on).

For comparison, our size-scaling estimate for this combination is 37.4 tok/s.

Every run

Quant	Backend	Generate tok/s	Prompt tok/s	Test	Build / by / notes	Source
Q8_0	CUDA FA on	48.7	2,364	tg32	ggml-org maintainers Benchmarked repo: https://huggingface.co/ggml-org/GLM-4.7-Flash-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) · GLM-4.7-Flash on other hardware