DGX Spark

Name: DGX Spark
Brand: NVIDIA
Price: 197899 TWD

NVIDIA DGX Spark: 64–128 GB of memory at 273 GB/s. Below: the open models it can run, estimated at 128 GB with an 8K context. A small CUDA Linux box with 128 GB of unified memory: it holds 120B-class models, but its 273 GB/s bandwidth limits generation speed. It launched at $3,999, and NVIDIA has since raised the price.

Last updated: 2026-10-14

Specifications

Memory	64–128 GB LPDDR5X[src]
Memory bandwidth	273 GB/s[src]
Power	140 W[src]
Launch	2025-10[src]
Launch price	US$3,999[src]
Architecture	Grace Blackwell (GB10: Blackwell GPU + 20-core Arm CPU)[src]
Software	CUDA

What it can run

Best-quality quantization that fits with a 8K context, and the estimated generation speed. Estimates, not benchmarks. See the methodology.

Memory configuration

Model	Params	Best quant	Memory	tok/s (est.)
Qwen3.5-122B-A10B	122B (10B)	Q5_K_M	85.5 GiB	23
Mistral Small 4 119B (2603)	119B (6.5B)	Q5_K_M	83.4 GiB	35
gpt-oss-120b	117B (5.1B)	Q6_K	95.0 GiB	39
Llama 4 Scout 17B-16E Instruct	109B (17B)	Q6_K	89.8 GiB	12
GLM-4.5-Air	106B (12B)	Q6_K	87.3 GiB	17
Qwen3-Coder-Next (80B-A3B)	80B (3B)	Q8_0	83.8 GiB	51
Llama 3.3 70B Instruct	70B	Q8_0	75.7 GiB	2.2
Qwen3.5-35B-A3B	35B (3B)	FP16	69.1 GiB	27
Qwen3.6-35B-A3B	35B (3B)	FP16	69.1 GiB	27
Qwen3-32B	32.8B	FP16	66.6 GiB	2.5
DeepSeek-R1-Distill-Qwen-32B	32.76B	FP16	66.6 GiB	2.5
Gemma 4 31B IT	30.7B	FP16	61.6 GiB	2.7
Qwen3-30B-A3B (2507)	30.5B (3.3B)	FP16	60.9 GiB	25
Qwen3-Coder-30B-A3B-Instruct	30.5B (3.3B)	FP16	60.9 GiB	25
GLM-4.7-Flash (30B-A3B)	30B (3B)	FP16	59.6 GiB	27
Qwen3.5-27B	27B	FP16	53.8 GiB	3.0
Qwen3.6-27B	27B	FP16	53.8 GiB	3.0
Qwen3.8-27B	27B	FP16	53.8 GiB	3.0
Gemma 3 27B IT	27B	FP16	54.3 GiB	3.0
Gemma 4 26B A4B IT	25.2B (3.8B)	FP16	50.1 GiB	22
Mistral Small 3.2 24B Instruct (2506)	24B	FP16	48.7 GiB	3.4
Magistral Small 1.2 (2509)	24B	FP16	48.7 GiB	3.4
Devstral Small 2 24B Instruct (2512)	24B	FP16	48.7 GiB	3.4
gpt-oss-20b	21B (3.6B)	FP16	41.8 GiB	23
Phi-4 (14B)	14B	FP16	29.4 GiB	5.9
Gemma 3 12B IT	12B	FP16	24.8 GiB	6.8
Gemma 4 12B Unified IT	11.95B	FP16	24.2 GiB	6.9
Qwen3.5-9B	9B	FP16	18.4 GiB	9.1
Qwen3-8B	8.2B	FP16	17.7 GiB	10.0
DeepSeek-R1-0528-Qwen3-8B	8.19B	FP16	17.6 GiB	10
Llama 3.1 8B Instruct	8B	FP16	17.1 GiB	10
Gemma 4 E4B IT	8B	FP16	16.4 GiB	10
Llama 3.2 3B Instruct	3.21B	FP16	7.7 GiB	26
Kimi K2.6	1000B (32B)	Doesn't fit	–	–
DeepSeek-R1-0528 (671B)	671B (37B)	Doesn't fit	–	–
DeepSeek-V4-Flash	284B (13B)	Doesn't fit	–	–
Qwen3.8-Flash-Next	180B (6B)	Doesn't fit	–	–

Prices

Latest price at each shop, as listed on the day we checked.

Region	Shop	Listing	Price	Per GB	Checked
Taiwan	momo購物網摩天商城 store TP0002353	【麗臺科技】Leadtek NVIDIA DGX Spark GB10 / 128G / Gen4 4TB SSD桌上型AI超級電腦Third-party store inside momo; the page does not name the seller	NT$197,899	NT$1,546/GB	2026-10-14
Taiwan	原價屋 CoolPC	NVIDIA DGX Spark GB10 / 128G / Gen4 4TB SSDLine on the shop's public price list (no per-product page); list stamped 2026/10/14 15:47	NT$199,500	NT$1,559/GB	2026-10-14
US	NVIDIA Marketplace	NVIDIA DGX Spark, 128GB unified memory, 4TB NVMe	US$6,950	US$54/GB	2026-10-14

Taiwan value: about 33.8 tok/s on Llama 3.1 8B Instruct (Q4_K_M, 8K), or 0.2 tok/s per NT$1,000.
US value: about 33.8 tok/s on Llama 3.1 8B Instruct (Q4_K_M, 8K), or 0.5 tok/s per US$100.

A price history chart appears once we have checked this device on two or more days.

All prices →

Frequently asked questions

Which LLMs can the DGX Spark run?

With 128 GB and an 8K context, the largest models that fit include: Qwen3.5-122B-A10B, Mistral Small 4 119B (2603), gpt-oss-120b, Llama 4 Scout 17B-16E Instruct, GLM-4.5-Air. See the full table below.

How fast is the DGX Spark for local LLMs?

Generation speed is mostly set by memory bandwidth (273 GB/s). For Llama 3.1 8B Instruct at FP16, expect roughly 10 tokens/s; bigger models are slower.

Can the DGX Spark run 70B models?

Yes. Llama 3.3 70B Instruct fits on the DGX Spark (128 GB) at Q8_0 with an 8K context, using about 75.7 GiB, at an estimated 2.2 tokens/s.