readygpu

ASUS Ascent GX10 128GB vs NVIDIA GeForce RTX 4090

For running models locally, priced in Canada. At 8k context the first runs 70 models fully in memory, the second 51.

In short

The ASUS Ascent GX10 128GB has more memory for models: 128 GB against 24 GB. At 8k context the ASUS Ascent GX10 128GB runs 70 of the models we track fully in memory and the NVIDIA GeForce RTX 4090 51; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash. On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 3.7× 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 GeForce RTX 4090 $7,107 at Amazon: the NVIDIA GeForce RTX 4090 is $1,192 cheaper.

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

ASUS Ascent GX10 128GB

$8,299

Amazon

Add to build
NVIDIA GeForce RTX 4090

$7,107

Amazon

Add to build

Specifications

SpecASUS Ascent GX10 128GBNVIDIA GeForce RTX 4090
ChipGB10 Grace Blackwell–
Memory bus256-bit384-bit
Memory bandwidth273 GB/s1,008 GB/s
FP16 compute62 TFLOPS165 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–GeForce RTX 4090
Memory–24 GB GDDR6X
Board power–450 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 GeForce RTX 4090
DeepSeek V4 Flash14tok/sUD-Q2_K_XLwon't run
GLM 5.3 Flash12tok/sUD-Q2_K_XLwon't run
Qwen 3.8 Flash Next3tok/sQ4_K_Mwon't run
MiniMax M2.715tok/sUD-Q3_K_Mwon't run
Qwen 3.8 27B6tok/sQ8_028tok/sUD-Q6_K
Qwen 3.5 122B-A10B12tok/sQ6_Koffload
Qwen 3.6 27B6tok/sQ8_027tok/sQ6_K
gpt-oss 120B30tok/sMXFP4won't run
Qwen3 Coder Next23tok/sQ8_0offload
Nemotron 3 Super 120B-A12B9tok/sUD-Q6_Kwon't run
Gemma 4 31B5tok/sQ8_027tok/sQ5_K_M
Mistral Small 4 119B13tok/sQ8_0offload
Qwen 3.6 35B-A3B31tok/sQ8_0179tok/sQ4_K_M
Qwen 3.5 27B6tok/sQ8_027tok/sQ6_K
Gemma 4 26B-A4B22tok/sQ8_095tok/sUD-Q6_K
GLM 4.5 Air5tok/sQ8_0offload
Qwen 3.5 35B-A3B31tok/sQ8_0181tok/sQ4_K_M
Qwen3 Next 80B-A3B30tok/sQ8_0offload
GLM 4.7 Flash18tok/sQ8_094tok/sQ5_K_M
Devstral Small 2 24B6tok/sQ8_030tok/sQ6_K
Nemotron 3.5 Lightning 30B-A3B30tok/sUD-Q6_K_XLoffload
gpt-oss 20B39tok/sMXFP4142tok/sMXFP4
Kimi Linear 48B-A3B31tok/sQ8_0offload
Qwen3 Coder 30B-A3B25tok/sQ8_0128tok/sQ5_K_M
Qwen3 32B5tok/sQ8_029tok/sQ4_K_M
Gemma 4 12B13tok/sQ8_048tok/sQ8_0
Qwen 3.5 9B17tok/sQ8_064tok/sQ8_0
Mistral Small 3.2 24B6tok/sQ8_030tok/sQ6_K
Gemma 3 27B6tok/sQ8_027tok/sQ6_K
DeepSeek R1 Distill Qwen 32B5tok/sQ8_028tok/sQ4_K_M
Llama 3.3 70B2tok/sQ8_0offload
Ministral 3 14B11tok/sQ8_040tok/sQ8_0
Qwen3 14B10tok/sQ8_037tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B17tok/sQ8_063tok/sQ8_0
Qwen3 8B17tok/sQ8_063tok/sQ8_0
Phi-4 14B10tok/sQ8_036tok/sQ8_0
Qwen 3.5 4B35tok/sQ8_0130tok/sQ8_0
Ministral 3 8B17tok/sQ8_062tok/sQ8_0
Granite 4.2 8B16tok/sQ8_059tok/sQ8_0
Gemma 4 E4B20tok/sQ8_074tok/sQ8_0
LFM2.5 8B-A1B69tok/sQ8_0256tok/sQ8_0
Llama 3.1 8B22tok/sQ6_K82tok/sQ6_K
Qwen2.5 0.5B268tok/sQ8_0989tok/sQ8_0
Qwen3.5 0.8B182tok/sQ8_0671tok/sQ8_0
Qwen3.5 2B109tok/sQ5_K_M402tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B80tok/sQ8_0294tok/sQ8_0
MiniCPM5 2B56tok/sQ8_0206tok/sQ8_0
LFM2.5 2.6B50tok/sQ8_0185tok/sQ8_0
LFM2.5 VL 3B50tok/sQ8_0185tok/sQ8_0
granite vision 4.1 4b39tok/sQ8_0146tok/sQ8_0
granite 4.2 3b37tok/sQ8_0137tok/sQ8_0
LFM2.5 24B A2B36tok/sQ8_0154tok/sQ6_K
Mellum2.1 12B A2.5B Thinking36tok/sQ8_0133tok/sQ8_0
Kimi VL A3B29tok/smlx-8bit107tok/smlx-8bit
DeepSeek R1 Distill Qwen 7B20tok/sQ8_073tok/sQ8_0
DeepSeek R1 Distill Llama 8B18tok/sQ8_065tok/sQ8_0
Ministral 3 8B Reasoning 251217tok/sQ8_062tok/sQ8_0
GLM 4.6V Flash16tok/sQ8_061tok/sQ8_0
GLM 4.1V 9B Thinking14tok/smlx-8bit52tok/smlx-8bit
MiniMax M2.513tok/sMXFP4won't run
DeepSeek R1 Distill Qwen 14B10tok/sQ8_036tok/sQ8_0
Devstral Small 25076tok/sQ8_035tok/sQ5_K_M
Magistral Small 25066tok/sQ8_030tok/sQ6_K
Magistral Small 25076tok/sQ8_035tok/sQ5_K_M
Magistral Small 25096tok/sQ8_035tok/sQ5_K_M
GLM 4.5V6tok/sQ8_0won't run
GLM 4.6V6tok/sQ8_0won't run
granite 4.2 30b5tok/sQ8_027tok/sQ5_K_M
DeepSeek R1 Distill Llama 70B2tok/sQ8_0offload
Mistral Medium 3.5 128B2tok/sQ6_Kwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won'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
Devstral 2 123B Instruct 2512won't runwon't run
GLM 4.7won'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 M3won't runwon't run

Questions

Which is better for local AI, the ASUS Ascent GX10 128GB or the NVIDIA GeForce RTX 4090?
Choose the ASUS Ascent GX10 128GB to run bigger models. Choose the NVIDIA GeForce RTX 4090 for speed. Choose the NVIDIA GeForce RTX 4090 to spend less.
Which can run bigger models, the ASUS Ascent GX10 128GB or the NVIDIA GeForce RTX 4090?
At 8k context the ASUS Ascent GX10 128GB runs 70 of the models we track fully in memory and the NVIDIA GeForce RTX 4090 51; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash.
Which is faster for local AI, the ASUS Ascent GX10 128GB or the NVIDIA GeForce RTX 4090?
On the models both run fully in memory, the NVIDIA GeForce RTX 4090 is about 3.7× 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 GeForce RTX 4090?
In Canada the ASUS Ascent GX10 128GB costs $8,299 at Amazon and the NVIDIA GeForce RTX 4090 $7,107 at Amazon: the NVIDIA GeForce RTX 4090 is $1,192 cheaper.

More comparisons