readygpu

ASUS Ascent GX10 128GB vs NVIDIA RTX PRO 6000 Blackwell

For running models locally, priced in the US. At 128k context the first runs 76 models fully in memory, the second 70.

In short

The ASUS Ascent GX10 128GB has more memory for models: 128 GB against 96 GB. At 128k context the ASUS Ascent GX10 128GB runs 76 of the models we track fully in memory and the NVIDIA RTX PRO 6000 Blackwell 70; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash. On the models both run fully in memory, the NVIDIA RTX PRO 6000 Blackwell is about 6.6× as fast as the ASUS Ascent GX10 128GB (estimated, median across models). In the US the ASUS Ascent GX10 128GB costs $6,999 at eBay and the NVIDIA RTX PRO 6000 Blackwell $8,000 at Amazon: the ASUS Ascent GX10 128GB is $1,001 cheaper.

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

ASUS Ascent GX10 128GB

$6,999

eBay

Add to build
NVIDIA RTX PRO 6000 Blackwell

$8,000

Amazon

Add to build

Specifications

SpecASUS Ascent GX10 128GBNVIDIA RTX PRO 6000 Blackwell
ChipGB10 Grace Blackwell–
Memory bus256-bit512-bit
Memory bandwidth273 GB/s1,792 GB/s
FP16 compute62 TFLOPS504 TFLOPS
SoftwareCUDACUDA
Unified memory128 GB–
GPU can use by default119 GB–
GPU can use, tuned122 GB–
Operating systemdgx-os–
Processor20-core Arm (GB10)–
Storage1000 GB–
GPU–RTX PRO 6000 Blackwell
Memory–96 GB GDDR7
Board power–600 W
PCIe generation–Gen 5
PCIe lanes–x16

What each runs

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

ModelASUS Ascent GX10 128GBNVIDIA RTX PRO 6000 Blackwell
DeepSeek V4 Flash6tok/sUD-Q2_K_XLoffload
GLM 5.3 Flash10tok/sUD-Q2_K_XLoffload
Qwen 3.8 Flash Next2tok/sQ4_K_M20tok/sUD-Q3_K_XL
Qwen 3.8 27B5tok/sQ8_029tok/sQ8_0
MiniMax M2.73tok/sUD-Q2_K_XLoffload
Qwen 3.5 122B-A10B9tok/sQ6_K62tok/sQ5_K_M
Qwen 3.6 27B5tok/sQ8_030tok/sQ8_0
Qwen3 Coder Next14tok/sQ8_090tok/sQ8_0
gpt-oss 120B13tok/sMXFP484tok/sMXFP4
Nemotron 3 Super 120B-A12B8tok/sUD-Q6_K63tok/sQ5_K_M
Gemma 4 31B4tok/sQ8_025tok/sQ8_0
Mistral Small 4 119B11tok/sUD-Q6_K76tok/sQ6_K
Qwen 3.6 35B-A3B17tok/sQ8_0114tok/sQ8_0
Qwen 3.5 27B5tok/sQ8_030tok/sQ8_0
Gemma 4 26B-A4B14tok/sQ8_095tok/sQ8_0
GLM 4.5 Air3tok/sQ6_K20tok/sQ4_K_M
Qwen 3.5 35B-A3B17tok/sQ8_0114tok/sQ8_0
Qwen3 Next 80B-A3B16tok/sQ8_0104tok/sQ8_0
GLM 4.7 Flash8tok/sQ8_054tok/sQ8_0
Devstral Small 2 24B4tok/sQ8_024tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3B24tok/sUD-Q6_K_XL160tok/sUD-Q6_K_XL
Kimi Linear 48B-A3B24tok/sQ8_0155tok/sQ8_0
gpt-oss 20B18tok/sMXFP4118tok/sMXFP4
Qwen3 Coder 30B-A3B6tok/sQ8_042tok/sQ8_0
Qwen3 32B2tok/sQ8_016tok/sQ8_0
Gemma 4 12B11tok/sQ8_073tok/sQ8_0
Qwen 3.5 9B12tok/sQ8_080tok/sQ8_0
Gemma 3 27B4tok/sQ8_028tok/sQ8_0
Mistral Small 3.2 24B4tok/sQ8_024tok/sQ8_0
DeepSeek R1 Distill Qwen 32B2tok/sQ8_016tok/sQ8_0
Llama 3.3 70B1tok/sQ8_012tok/sQ5_K_M
Ministral 3 14B5tok/sQ8_031tok/sQ8_0
Qwen3 14B5tok/sQ8_030tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B6tok/sQ8_040tok/sQ8_0
Qwen3 8B6tok/sQ8_040tok/sQ8_0
Phi-4 14B4tok/sQ8_026tok/sQ8_0
Qwen 3.5 4B19tok/sQ8_0126tok/sQ8_0
Ministral 3 8B6tok/sQ8_041tok/sQ8_0
Granite 4.2 8B6tok/sQ8_036tok/sQ8_0
Gemma 4 E4B14tok/sQ8_093tok/sQ8_0
LFM2.5 8B-A1B14tok/sQ8_089tok/sQ8_0
Llama 3.1 8B7tok/sQ6_K47tok/sQ6_K
Qwen2.5 0.5B79tok/sQ8_0519tok/sQ8_0
Qwen3.5 0.8B69tok/sQ8_0455tok/sQ8_0
Qwen3.5 2B55tok/sQ5_K_M363tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B30tok/sQ8_0197tok/sQ8_0
Mellum2.1 12B A2.5B Thinking22tok/sQ8_0146tok/sQ8_0
Spark X2.5 4B21tok/smlx-4bit140tok/smlx-4bit
MiniCPM5 2B20tok/sQ8_0134tok/sQ8_0
FrogNano 4B 260919tok/sQ8_0124tok/sQ8_0
LFM2.5 2.6B16tok/sQ8_0102tok/sQ8_0
LFM2.5 VL 3B16tok/sQ8_0102tok/sQ8_0
Kimi VL A3B Thinking 250614tok/sQ8_093tok/sQ8_0
Kimi VL A3B14tok/smlx-8bit91tok/smlx-8bit
GLM 4 9B 041412tok/smlx-5bit82tok/smlx-5bit
granite vision 4.1 4b12tok/sQ8_077tok/sQ8_0
granite 4.2 3b12tok/sQ8_076tok/sQ8_0
GLM 4.6V Flash11tok/sQ8_072tok/sQ8_0
DeepSeek R1 Distill Qwen 7B11tok/sQ8_071tok/sQ8_0
GLM 4.1V 9B Thinking10tok/smlx-8bit65tok/smlx-8bit
LFM2.5 24B A2B8tok/sQ8_052tok/sQ8_0
DeepSeek R1 Distill Llama 8B7tok/sQ8_043tok/sQ8_0
Ministral 3 8B Reasoning 25126tok/sQ8_041tok/sQ8_0
Qwen3.8 27B OBLITERATED6tok/smlx-4bit38tok/smlx-4bit
DeepSeek R1 Distill Qwen 14B4tok/sQ8_027tok/sQ8_0
Devstral Small 25074tok/sQ8_024tok/sQ8_0
Magistral Small 25064tok/sQ8_024tok/sQ8_0
Magistral Small 25074tok/sQ8_024tok/sQ8_0
Magistral Small 25094tok/sQ8_024tok/sQ8_0
GLM 4.5V3tok/sQ4_K_M20tok/sQ4_K_M
GLM 4.6V3tok/sQ4_K_M20tok/sQ4_K_M
granite 4.2 30b3tok/sQ8_017tok/sQ8_0
DeepSeek R1 Distill Llama 70B1tok/sQ8_012tok/sQ5_K_M
Devstral 2 123B Instruct 25121tok/sQ4_K_Moffload
Kimi Dev 72B1tok/sQ8_0offload
Mistral Medium 3.5 128B1tok/sQ4_K_Moffload
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Zerowon'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 ASUS Ascent GX10 128GB or the NVIDIA RTX PRO 6000 Blackwell?
Choose the ASUS Ascent GX10 128GB to run bigger models. Choose the NVIDIA RTX PRO 6000 Blackwell for speed. Choose the ASUS Ascent GX10 128GB to spend less.
Which can run bigger models, the ASUS Ascent GX10 128GB or the NVIDIA RTX PRO 6000 Blackwell?
At 128k context the ASUS Ascent GX10 128GB runs 76 of the models we track fully in memory and the NVIDIA RTX PRO 6000 Blackwell 70; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash.
Which is faster for local AI, the ASUS Ascent GX10 128GB or the NVIDIA RTX PRO 6000 Blackwell?
On the models both run fully in memory, the NVIDIA RTX PRO 6000 Blackwell is about 6.6× as fast as the ASUS Ascent GX10 128GB (estimated, median across models).
What is the price difference between the ASUS Ascent GX10 128GB and the NVIDIA RTX PRO 6000 Blackwell?
In the US the ASUS Ascent GX10 128GB costs $6,999 at eBay and the NVIDIA RTX PRO 6000 Blackwell $8,000 at Amazon: the ASUS Ascent GX10 128GB is $1,001 cheaper.

More comparisons