DGX Spark (GH200 480GB) vs RTX 5060 Ti 16GB for Local LLMs

The DGX Spark (GH200 480GB) has about 12% more memory bandwidth (500 vs 448 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 12% faster on the DGX Spark (GH200 480GB). The DGX Spark (GH200 480GB) fits more of the catalog at Q4/8K — 66 vs 24 of 69 models (480 vs 16 GB VRAM). Largest model that fits the DGX Spark (GH200 480GB) but not the RTX 5060 Ti 16GB: DeepSeek-V4-Pro (861.6B). MSRP is $3,000 for the DGX Spark (GH200 480GB) vs $429 for the RTX 5060 Ti 16GB. MSRP is a launch list price, not live retail — Amazon prices move; click through for the current price. In the Q4/8K head-to-head below (44 shared models), the DGX Spark (GH200 480GB) posts the higher tok/s in 26 rows vs 15. Methodology.

Spec comparison

	DGX Spark (GH200 480GB)	RTX 5060 Ti 16GB
Vendor	NVIDIA	NVIDIA
VRAM	480 GB	16 GB
Memory type	LPDDR5X	GDDR7
Memory bandwidth	500 GB/s	448 GB/s
TDP	170 W	180 W
MSRP (list)	$3,000	$429
Buy	Search Amazon (affiliate)	Search Amazon (affiliate)

MSRP is the launch list price, not live retail. Buy links are Amazon affiliate links — the price after you click is the live price.

Q4 / 8K head-to-head — top 15 of 44 shared models

Model	Params (B)	DGX Spark (GH200 480GB) tok/s	DGX Spark (GH200 480GB) fits	RTX 5060 Ti 16GB tok/s	RTX 5060 Ti 16GB fits	Winner
MiniCPM5-1B	1.08	294.6 est.	Yes	264.0 est.	Yes	DGX Spark (GH200 480GB)
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16	30.0	106.1 est.	Yes	225.5 est.	No	RTX 5060 Ti 16GB
Qwen3-30B-A3B-Instruct-2507	30.5	106.1 est.	Yes	205.1 est.	No	RTX 5060 Ti 16GB
GLM-4.7-Flash	31.2	106.1 est.	Yes	196.9 est.	No	RTX 5060 Ti 16GB
Qwen3.5-35B-A3B	34.7	106.1 est.	Yes	170.5 est.	No	RTX 5060 Ti 16GB
qwen35b-a3b-fable-sft-abliterated	34.7	106.1 est.	Yes	161.9 est.	No	RTX 5060 Ti 16GB
Ornith-1.0-35B	35.0	106.1 est.	Yes	159.4 est.	No	RTX 5060 Ti 16GB
Qwen3.5-2B	2.0	159.1 est.	Yes	142.5 est.	Yes	DGX Spark (GH200 480GB)
Qwen3.6-35B-A3B	36.0	106.1 est.	Yes	158.9 est.	No	RTX 5060 Ti 16GB
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx	2.3	138.3 est.	Yes	124.0 est.	Yes	DGX Spark (GH200 480GB)
gpt-oss-20b	21.5	88.4 est.	Yes	111.5 measured	Yes	RTX 5060 Ti 16GB
Qwen3-Coder-Next	79.7	106.1 est.	Yes	34.4 est.	No	DGX Spark (GH200 480GB)
Qwen3-Next-80B-A3B-Instruct	81.3	106.1 est.	Yes	33.0 est.	No	DGX Spark (GH200 480GB)
Llama-3.2-3B-Instruct	3.2	99.4 est.	Yes	89.1 est.	Yes	DGX Spark (GH200 480GB)
Mistral-7B-Instruct-v0.3	7.2	44.2 est.	Yes	91.1 measured	Yes	RTX 5060 Ti 16GB

est. = bandwidth-based estimate; measured = curated real benchmark that overrides the estimate. Fits = weights + KV(8K) + 1 GB overhead ≤ 95% of VRAM.

Fit coverage at Q4 / 8K

	DGX Spark (GH200 480GB)	RTX 5060 Ti 16GB
Catalog models that fit	66 of 69	24 of 69
Largest exclusive fit	DeepSeek-V4-Pro (861.6B)	—

DGX Spark (GH200 480GB) details → · RTX 5060 Ti 16GB details →