DGX Spark

Nvidia · 128 GB VRAM · MSRP $3,999

48recorded runs

86.8best tok/s

48sourced

Evidence: 48 sourced runs · 1 independent source · first recorded Aug 20, 2026 · last recorded Oct 16, 2026. What these labels mean.

All benchmarks Compare DGX Spark →

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
DGX Spark · 128 GB	Qwen 3.8 Flash	EXL3 3.05bpw	exllamav2 523ecd3	2048	86.8 ✓	—	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	4.05bpw_h6_ng6	tensorfold 0.6.5	40960	75.7 ✓	—	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	EXL3	exllamav2 523ecd3	240000	72.0 ✓	—	—	src
DGX Spark · 128 GB	Qwen 3.8 Flash	EXL3 3.05bpw	exllamav2 523ecd3	600	71.7 ✓	—	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	EXL3	exllamav2 523ecd3	4000	69.8 ✓	—	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	EXL3	exllamav2 523ecd3	128000	69.5 ✓	—	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	EXL3 3.05bpw	exllamav2 523ecd3	75000	67.6 ✓	—	—	src
DGX Spark · 128 GB	Qwen 3.8 Flash	EXL3 3.05bpw	exllamav2 523ecd3	64000	67.4 ✓	—	—	src
DGX Spark · 128 GB	Qwen 3.8 Flash	EXL3 3.05bpw	exllamav2 523ecd3	110000	66.0 ✓	—	—	src
DGX Spark · 128 GB	GLM-5.3-Flash	EXL3 2.05 bpw	vllm sha256:905c02933be6021301db2dc284e24…	262144	64.1 ✓	—	—	src
DGX Spark · 128 GB	GLM-5.3-Flash	EXL3 2.05 bpw	vllm sha256:905c02933be6021301db2dc284e24…	512	64.1 ✓	—	—	src
DGX Spark · 128 GB	CYBER-FROST-3.8	EXL3	exllamav2 047ce72	400	60.7 ✓	—	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next-hibrid48	NVFP4 (output head)	vllm 0.29.0	262000	60.0 ✓	—	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	EXL3 3.05bpw	exllamav2 523ecd3	32000	59.0 ✓	—	—	src
DGX Spark · 128 GB	Qwen 3.8 Flash	EXL3 3.05bpw	exllamav2 523ecd3	35000	58.0 ✓	980.0	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	EXL3 3.05bpw	exllamav2 523ecd3	1000	56.0 ✓	—	—	src
DGX Spark · 128 GB	Qwen3.8-27B	NVFP4 W4A4	sglang lmsysorg/sglang:dev-qwen38-27b-dflas…	262144	56.0 ✓	—	—	src
DGX Spark · 128 GB	Qwen 3.8 Flash	EXL3 3.05bpw	exllamav2 523ecd3	240000	55.8 ✓	—	—	src
DGX Spark · 128 GB	Qwen 3.8 Flash	EXL3 3.05bpw	exllamav2 523ecd3	32000	55.6 ✓	—	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	NVFP4	sglang 8874c51a	262144	55.0 ✓	—	—	src
DGX Spark · 128 GB	Qwen 3.8 Flash	EXL3 3.05bpw	exllamav2 523ecd3	8000	51.5 ✓	—	—	src
DGX Spark · 128 GB	Qwen3.8-27B	NVFP4 W4A4	sglang lmsysorg/sglang:qwen38-27b	262144	51.5 ✓	—	—	src
DGX Spark · 128 GB	NVIDIA-Nemotron-3.5-Super-VL-120B-A12B	NVFP4	vllm vllm/vllm-openai@sha256:cb9bc64f… …	262144	48.0 ✓	—	—	src
DGX Spark · 128 GB	DeepSeek-V4.1-Flash	FP4	custom v41_engine.py v0.1.0-wip (2026-09-10)	32768	47.0 ✓	—	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	NVFP4+FP8 hybrid	vllm blazux/qwen3.8-Flash-DGX (vllm fork)…	258790	44.2 ✓	1636.7	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	NVFP4	vllm 8a728663	262144	43.9 ✓	—	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	NVFP4+FP8 hybrid	vllm blazux/qwen3.8-Flash-DGX (vllm fork)…	4292	43.0 ✓	1417.3	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	NVFP4+FP8 hybrid	vllm blazux/qwen3.8-Flash-DGX (vllm fork)…	32850	42.6 ✓	1491.4	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	NVFP4+FP8 hybrid	vllm blazux/qwen3.8-Flash-DGX (vllm fork)…	16424	42.3 ✓	1322.3	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	NVFP4+FP8 hybrid	vllm blazux/qwen3.8-Flash-DGX (vllm fork)…	8232	42.1 ✓	1414.9	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	NVFP4+FP8 hybrid	vllm blazux/qwen3.8-Flash-DGX (vllm fork)…	864	41.6 ✓	580.6	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	NVFP4+FP8 hybrid	vllm blazux/qwen3.8-Flash-DGX (vllm fork)…	66177	41.4 ✓	1780.4	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	NVFP4+FP8 hybrid	vllm blazux/qwen3.8-Flash-DGX (vllm fork)…	2271	41.1 ✓	1132.0	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	NVFP4+FP8 hybrid	vllm blazux/qwen3.8-Flash-DGX (vllm fork)…	131437	40.6 ✓	1718.3	—	src
DGX Spark · 128 GB	Qwen3.8-Flash-Next	NVFP4+FP8 hybrid	vllm blazux/qwen3.8-Flash-DGX (vllm fork)…	327	37.4 ✓	132.0	—	src
DGX Spark · 128 GB	GLM-5.3-Flash	EXL3 2.05 bpw	vllm sha256:905c02933be6021301db2dc284e24…	40000	35.5 ✓	—	—	src
DGX Spark · 128 GB	Underdog-Saluki-27B	IQ2-mix	llama.cpp b11459 (f498f864f)	262144	22.6 ✓	—	—	src
DGX Spark · 128 GB	DeepSeek-V4.1-Flash	FP4	custom v41_engine.py v0.3.0-wip (3.3 addendum)	32768	22.1 ✓	—	—	src
DGX Spark · 128 GB	DeepSeek-V4.1-Flash	FP4	custom v41_engine.py v0.3.0-wip (commit 94a96a6..)	32768	20.9 ✓	—	—	src
DGX Spark · 128 GB	DeepSeek-V4.1-Flash	FP4	custom triton-based engine (v41_ bd24743..22bd9a8+ (v0.2.0-wip), then…	32768	20.9 ✓	—	—	src
DGX Spark · 128 GB	DeepSeek-V4.1-Flash	FP4	custom v41_engine.py v0.3.0-wip (3.2 addendum)	32768	20.9 ✓	—	—	src
DGX Spark · 128 GB	DeepSeek-V4.1-Flash	FP4	custom v41_engine.py v0.2.0-wip (commits bd24743..22bd9a8…	8192	16.9 ✓	—	—	src
DGX Spark · 128 GB	DeepSeek-V4.1-Flash	FP4	custom v41_engine.py v0.2.0-wip (2.9 addendum)	8192	16.9 ✓	—	—	src
DGX Spark · 128 GB	DeepSeek-V4.1-Flash	FP4	custom triton-based engine (v41_ 9f172fb (v0.2.0-wip addendum 2.6)	8192	15.4 ✓	—	—	src
DGX Spark · 128 GB	DeepSeek-V4.1-Flash	FP4	custom v41_engine.py v0.2.0-wip (9f172fb)	8192	15.4 ✓	—	—	src
DGX Spark · 128 GB	DeepSeek-V4.1-Flash	FP4	custom triton-based engine (v41_ 22bd9a8 (v0.2.0-wip baseline)	8192	13.0 ✓	—	—	src
DGX Spark · 128 GB	DeepSeek-V4.1-Flash	FP4	custom v41_engine.py v0.2.0-wip (bd24743..22bd9a8+)	8192	12.9 ✓	—	—	src
DGX Spark · 128 GB	DeepSeek-V4.1-Flash	FP4	custom v41_engine.py v0.1.0-wip	32768	2.7 ✓	—	—	src

Related reading: GPU buying guide · used GPUs · Value index · Street prices