readygpu

NVIDIA DGX Spark 128GB vs NVIDIA RTX 6000 Ada Generation

For running models locally, priced in the US. At 128k context the first runs 79 models fully in memory, the second 60.

In short

The NVIDIA DGX Spark 128GB has more memory for models: 128 GB against 48 GB. At 128k context the NVIDIA DGX Spark 128GB runs 79 of the models we track fully in memory and the NVIDIA RTX 6000 Ada Generation 60; only the NVIDIA DGX Spark 128GB holds DeepSeek V4 Flash. On the models both run fully in memory, the NVIDIA RTX 6000 Ada Generation is about 3.5× as fast as the NVIDIA DGX Spark 128GB (estimated, median across models). In the US the NVIDIA DGX Spark 128GB costs $7,850 at eBay and the NVIDIA RTX 6000 Ada Generation $8,495 at Amazon: the NVIDIA DGX Spark 128GB is $645 cheaper.

Updated . Speeds are estimates; how they are worked out.

NVIDIA DGX Spark 128GB

$7,850

eBay

Add to build
NVIDIA RTX 6000 Ada Generation

$8,495

Amazon

Add to build

Specifications

SpecNVIDIA DGX Spark 128GBNVIDIA RTX 6000 Ada Generation
ChipGB10 Grace Blackwell–
Memory bus256-bit384-bit
Memory bandwidth273 GB/s960 GB/s
FP16 compute62 TFLOPS91.1 TFLOPS
SoftwareCUDACUDA
Unified memory128 GB–
GPU can use by default119 GB–
GPU can use, tuned122 GB–
Operating systemdgx-os–
Processor20-core Arm (GB10)–
Storage4000 GB–
GPU–RTX 6000 Ada Generation
Memory–48 GB GDDR6
Board power–300 W
PCIe generation–Gen 4
PCIe lanes–x16

What each runs

Estimated decode speed with the most precise quant that fits each one est.

ModelNVIDIA DGX Spark 128GBNVIDIA RTX 6000 Ada Generation
DeepSeek V4 Flash6tok/sUD-Q2_K_XLwon't run
GLM 5.3 Flash10tok/sUD-Q2_K_XLwon't run
Qwen 3.8 Flash Next2tok/sQ4_K_Mwon't run
Qwen 3.8 27B5tok/sQ8_016tok/sQ8_0
MiniMax M2.73tok/sUD-Q2_K_XLwon't run
Qwen 3.5 122B-A10B9tok/sQ6_K53tok/sUD-Q2_K_XL
Qwen 3.6 27B5tok/sQ8_016tok/sQ8_0
Qwen3 Coder Next14tok/sQ8_0offload
gpt-oss 120B13tok/sMXFP4offload
Nemotron 3 Super 120B-A12B8tok/sUD-Q6_Koffload
Gemma 4 31B4tok/sQ8_014tok/sQ8_0
Mistral Small 4 119B11tok/sUD-Q6_K66tok/sUD-Q2_K_XL
Qwen 3.6 35B-A3B17tok/sQ8_061tok/sQ8_0
Qwen 3.5 27B5tok/sQ8_016tok/sQ8_0
Gemma 4 26B-A4B14tok/sQ8_051tok/sQ8_0
GLM 4.5 Air3tok/sQ6_Koffload
Qwen 3.5 35B-A3B17tok/sQ8_061tok/sQ8_0
Qwen3 Next 80B-A3B16tok/sQ8_0offload
GLM 4.7 Flash8tok/sQ8_029tok/sQ8_0
Devstral Small 2 24B4tok/sQ8_013tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3B24tok/sUD-Q6_K_XL86tok/sUD-Q6_K_XL
Kimi Linear 48B-A3B24tok/sQ8_0100tok/sQ6_K
gpt-oss 20B18tok/sMXFP463tok/sMXFP4
Qwen3 Coder 30B-A3B6tok/sQ8_022tok/sQ8_0
Qwen3 32B2tok/sQ8_0offload
Gemma 4 12B11tok/sQ8_039tok/sQ8_0
Qwen 3.5 9B12tok/sQ8_043tok/sQ8_0
Gemma 3 27B4tok/sQ8_015tok/sQ8_0
Mistral Small 3.2 24B4tok/sQ8_013tok/sQ8_0
DeepSeek R1 Distill Qwen 32B2tok/sQ8_0offload
Llama 3.3 70B1tok/sQ8_0won't run
Ministral 3 14B5tok/sQ8_017tok/sQ8_0
Qwen3 14B5tok/sQ8_016tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B6tok/sQ8_021tok/sQ8_0
Qwen3 8B6tok/sQ8_021tok/sQ8_0
Phi-4 14B4tok/sQ8_014tok/sQ8_0
Qwen 3.5 4B19tok/sQ8_067tok/sQ8_0
Ministral 3 8B6tok/sQ8_022tok/sQ8_0
Granite 4.2 8B6tok/sQ8_019tok/sQ8_0
Gemma 4 E4B14tok/sQ8_050tok/sQ8_0
LFM2.5 8B-A1B14tok/sQ8_048tok/sQ8_0
Llama 3.1 8B7tok/sQ6_K25tok/sQ6_K
Qwen2.5 0.5B79tok/sQ8_0278tok/sQ8_0
Qwen3.5 0.8B69tok/sQ8_0244tok/sQ8_0
Qwen3.5 2B55tok/sQ5_K_M194tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B30tok/sQ8_0105tok/sQ8_0
Mellum2.1 12B A2.5B Thinking22tok/sQ8_078tok/sQ8_0
Spark X2.5 4B21tok/smlx-4bit75tok/smlx-4bit
MiniCPM5 2B20tok/sQ8_072tok/sQ8_0
FrogNano 4B 260919tok/sQ8_066tok/sQ8_0
LFM2.5 2.6B16tok/sQ8_055tok/sQ8_0
LFM2.5 VL 3B16tok/sQ8_055tok/sQ8_0
Kimi VL A3B Thinking 250614tok/sQ8_050tok/sQ8_0
Kimi VL A3B14tok/smlx-8bit49tok/smlx-8bit
GLM 4 9B 041412tok/smlx-5bit44tok/smlx-5bit
granite vision 4.1 4b12tok/sQ8_042tok/sQ8_0
granite 4.2 3b12tok/sQ8_041tok/sQ8_0
GLM 4.6V Flash11tok/sQ8_039tok/sQ8_0
DeepSeek R1 Distill Qwen 7B11tok/sQ8_038tok/sQ8_0
GLM 4.1V 9B Thinking10tok/smlx-8bit35tok/smlx-8bit
Ministral 3 3B Instruct 251210tok/sQ8_034tok/sQ8_0
LFM2.5 24B A2B8tok/sQ8_028tok/sQ8_0
DeepSeek R1 Distill Llama 8B7tok/sQ8_023tok/sQ8_0
Ministral 3 8B Reasoning 25126tok/sQ8_022tok/sQ8_0
Qwen3.8 27B OBLITERATED6tok/smlx-4bit20tok/smlx-4bit
Muse Glimmer 30B5tok/sQ8_017tok/sQ8_0
Ministral 3 14B Reasoning 25125tok/sQ8_017tok/sQ8_0
DeepSeek R1 Distill Qwen 14B4tok/sQ8_014tok/sQ8_0
Devstral Small 25074tok/sQ8_013tok/sQ8_0
Magistral Small 25064tok/sQ8_013tok/sQ8_0
Magistral Small 25074tok/sQ8_013tok/sQ8_0
Magistral Small 25094tok/sQ8_013tok/sQ8_0
GLM 4.5V3tok/sQ4_K_Mwon't run
GLM 4.6V3tok/sQ4_K_Mwon't run
granite 4.2 30b3tok/sQ8_0offload
DeepSeek R1 Distill Llama 70B1tok/sQ8_0won't run
Devstral 2 123B Instruct 25121tok/sQ4_K_Mwon't run
Kimi Dev 72B1tok/sQ8_0won't run
Mistral Medium 3.5 128B1tok/sQ4_K_Mwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Zerowon't runwon't run
DeepSeek V3won't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won't runwon't run
DeepSeek V3.1 Terminuswon't runwon't run
DeepSeek V3.2won't runwon't run
DeepSeek V4 Flash 0731won't runwon't run
DeepSeek V4 Flash Vision Expwon't runwon't run
GLM 4.5won't runwon't run
GLM 4.6won't runwon't run
GLM 4.7won't runwon't run
GLM 5won't runwon't run
GLM 5.1won't runwon't run
GLM 5.2won't runwon't run
GLM 5.3won't runwon't run
Kimi K2won't runwon't run
Kimi K2 Instruct 0905won't runwon't run
Kimi K2 Thinkingwon't runwon't run
Kimi K2.5won't runwon't run
MiniMax M2won't runwon't run
MiniMax M2.1won't runwon't run
MiniMax M2.5won't runwon't run
MiniMax M3won't runwon't run

Questions

Which is better for local AI, the NVIDIA DGX Spark 128GB or the NVIDIA RTX 6000 Ada Generation?
Choose the NVIDIA DGX Spark 128GB to run bigger models. Choose the NVIDIA RTX 6000 Ada Generation for speed. Choose the NVIDIA DGX Spark 128GB to spend less.
Which can run bigger models, the NVIDIA DGX Spark 128GB or the NVIDIA RTX 6000 Ada Generation?
At 128k context the NVIDIA DGX Spark 128GB runs 79 of the models we track fully in memory and the NVIDIA RTX 6000 Ada Generation 60; only the NVIDIA DGX Spark 128GB holds DeepSeek V4 Flash.
Which is faster for local AI, the NVIDIA DGX Spark 128GB or the NVIDIA RTX 6000 Ada Generation?
On the models both run fully in memory, the NVIDIA RTX 6000 Ada Generation is about 3.5× as fast as the NVIDIA DGX Spark 128GB (estimated, median across models).
What is the price difference between the NVIDIA DGX Spark 128GB and the NVIDIA RTX 6000 Ada Generation?
In the US the NVIDIA DGX Spark 128GB costs $7,850 at eBay and the NVIDIA RTX 6000 Ada Generation $8,495 at Amazon: the NVIDIA DGX Spark 128GB is $645 cheaper.

More comparisons

More hardware for local AI