readygpu

ASUS Ascent GX10 128GB vs NVIDIA RTX A6000

For running models locally, priced in Canada. At 32k context the first runs 79 models fully in memory, the second 65.

In short

The ASUS Ascent GX10 128GB has more memory for models: 128 GB against 48 GB. At 32k context the ASUS Ascent GX10 128GB runs 79 of the models we track fully in memory and the NVIDIA RTX A6000 65; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash. On the models both run fully in memory, the NVIDIA RTX A6000 is about 2.8× as fast as the ASUS Ascent GX10 128GB (estimated, median across models). In Canada the ASUS Ascent GX10 128GB costs $8,299 at Amazon and the NVIDIA RTX A6000 $7,000 at Amazon: the NVIDIA RTX A6000 is $1,299 cheaper.

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

ASUS Ascent GX10 128GB

$8,299

Amazon

Add to build
NVIDIA RTX A6000

$7,000

Amazon

Add to build

Specifications

SpecASUS Ascent GX10 128GBNVIDIA RTX A6000
ChipGB10 Grace Blackwell–
Memory bus256-bit384-bit
Memory bandwidth273 GB/s768 GB/s
FP16 compute62 TFLOPS38.71 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 A6000
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.

ModelASUS Ascent GX10 128GBNVIDIA RTX A6000
DeepSeek V4 Flash11tok/sUD-Q2_K_XLwon't run
GLM 5.3 Flash11tok/sUD-Q2_K_XLwon't run
Qwen 3.8 Flash Next2tok/sQ4_K_Mwon't run
MiniMax M2.78tok/sUD-Q3_K_Mwon't run
Qwen 3.8 27B5tok/sQ8_015tok/sQ8_0
Qwen 3.5 122B-A10B11tok/sQ6_K66tok/sUD-Q2_K_XL
Qwen 3.6 27B6tok/sQ8_015tok/sQ8_0
gpt-oss 120B23tok/sMXFP4offload
Qwen3 Coder Next20tok/sQ8_088tok/sQ4_K_M
Nemotron 3 Super 120B-A12B9tok/sUD-Q6_Koffload
Gemma 4 31B5tok/sQ8_013tok/sQ8_0
Mistral Small 4 119B15tok/sUD-Q6_K91tok/sUD-Q2_K_XL
Qwen 3.6 35B-A3B27tok/sQ8_075tok/sQ8_0
Qwen 3.5 27B6tok/sQ8_015tok/sQ8_0
Gemma 4 26B-A4B20tok/sQ8_057tok/sQ8_0
GLM 4.5 Air5tok/sQ8_0offload
Qwen 3.5 35B-A3B27tok/sQ8_075tok/sQ8_0
Qwen3 Next 80B-A3B25tok/sQ8_0107tok/sQ4_K_M
GLM 4.7 Flash14tok/sQ8_041tok/sQ8_0
Devstral Small 2 24B6tok/sQ8_016tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3B28tok/sUD-Q6_K_XL80tok/sUD-Q6_K_XL
gpt-oss 20B31tok/sMXFP488tok/sMXFP4
Kimi Linear 48B-A3B29tok/sQ8_0103tok/sQ6_K
Qwen3 Coder 30B-A3B16tok/sQ8_045tok/sQ8_0
Qwen3 32B4tok/sQ8_011tok/sQ8_0
Gemma 4 12B13tok/sQ8_035tok/sQ8_0
Qwen 3.5 9B16tok/sQ8_045tok/sQ8_0
Mistral Small 3.2 24B6tok/sQ8_016tok/sQ8_0
Gemma 3 27B5tok/sQ8_015tok/sQ8_0
DeepSeek R1 Distill Qwen 32B4tok/sQ8_011tok/sQ8_0
Llama 3.3 70B2tok/sQ8_0offload
Ministral 3 14B9tok/sQ8_024tok/sQ8_0
Qwen3 14B8tok/sQ8_023tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B13tok/sQ8_035tok/sQ8_0
Qwen3 8B13tok/sQ8_035tok/sQ8_0
Phi-4 14B8tok/sQ8_021tok/sQ8_0
Qwen 3.5 4B30tok/sQ8_085tok/sQ8_0
Ministral 3 8B13tok/sQ8_035tok/sQ8_0
Granite 4.2 8B12tok/sQ8_032tok/sQ8_0
Gemma 4 E4B19tok/sQ8_052tok/sQ8_0
LFM2.5 8B-A1B38tok/sQ8_0107tok/sQ8_0
Llama 3.1 8B16tok/sQ6_K44tok/sQ6_K
Qwen2.5 0.5B181tok/sQ8_0510tok/sQ8_0
Qwen3.5 0.8B137tok/sQ8_0386tok/sQ8_0
Qwen3.5 2B91tok/sQ5_K_M256tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B60tok/sQ8_0168tok/sQ8_0
MiniCPM5 2B41tok/sQ8_0116tok/sQ8_0
Spark X2.5 4B39tok/smlx-4bit111tok/smlx-4bit
LFM2.5 2.6B35tok/sQ8_097tok/sQ8_0
LFM2.5 VL 3B35tok/sQ8_097tok/sQ8_0
Mellum2.1 12B A2.5B Thinking32tok/sQ8_090tok/sQ8_0
FrogNano 4B 260930tok/sQ8_083tok/sQ8_0
granite vision 4.1 4b27tok/sQ8_076tok/sQ8_0
granite 4.2 3b26tok/sQ8_072tok/sQ8_0
Kimi VL A3B Thinking 250625tok/sQ8_069tok/sQ8_0
Kimi VL A3B24tok/smlx-8bit67tok/smlx-8bit
Ministral 3 3B Instruct 251224tok/sQ8_067tok/sQ8_0
LFM2.5 24B A2B21tok/sQ8_059tok/sQ8_0
GLM 4 9B 041418tok/smlx-5bit50tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B17tok/sQ8_048tok/sQ8_0
GLM 4.6V Flash15tok/sQ8_042tok/sQ8_0
DeepSeek R1 Distill Llama 8B13tok/sQ8_037tok/sQ8_0
GLM 4.1V 9B Thinking13tok/smlx-8bit36tok/smlx-8bit
Ministral 3 8B Reasoning 251213tok/sQ8_035tok/sQ8_0
Ministral 3 14B Reasoning 25129tok/sQ8_024tok/sQ8_0
DeepSeek R1 Distill Qwen 14B8tok/sQ8_022tok/sQ8_0
Qwen3.8 27B OBLITERATED7tok/smlx-4bit21tok/smlx-4bit
Devstral Small 25076tok/sQ8_016tok/sQ8_0
Magistral Small 25066tok/sQ8_016tok/sQ8_0
Magistral Small 25076tok/sQ8_016tok/sQ8_0
Magistral Small 25096tok/sQ8_016tok/sQ8_0
Muse Glimmer 30B5tok/sQ8_015tok/sQ8_0
GLM 4.5V5tok/sQ8_0offload
GLM 4.6V5tok/sQ8_0offload
granite 4.2 30b4tok/sQ8_012tok/sQ8_0
DeepSeek R1 Distill Llama 70B2tok/sQ8_0offload
Kimi Dev 72B2tok/sQ8_0offload
Devstral 2 123B Instruct 25122tok/sQ6_Kwon't run
Mistral Medium 3.5 128B2tok/sQ6_Kwon'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 ASUS Ascent GX10 128GB or the NVIDIA RTX A6000?
Choose the ASUS Ascent GX10 128GB to run bigger models. Choose the NVIDIA RTX A6000 for speed. Choose the NVIDIA RTX A6000 to spend less.
Which can run bigger models, the ASUS Ascent GX10 128GB or the NVIDIA RTX A6000?
At 32k context the ASUS Ascent GX10 128GB runs 79 of the models we track fully in memory and the NVIDIA RTX A6000 65; 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 A6000?
On the models both run fully in memory, the NVIDIA RTX A6000 is about 2.8× 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 A6000?
In Canada the ASUS Ascent GX10 128GB costs $8,299 at Amazon and the NVIDIA RTX A6000 $7,000 at Amazon: the NVIDIA RTX A6000 is $1,299 cheaper.

More comparisons

More hardware for local AI