readygpu

ASUS Ascent GX10 128GB vs NVIDIA GeForce RTX 5090

For running models locally, priced in Canada. At 32k context the first runs 53 models fully in memory, the second 38.

In short

The ASUS Ascent GX10 128GB has more memory for models: 128 GB against 32 GB. At 32k context the ASUS Ascent GX10 128GB runs 53 of the models we track fully in memory and the NVIDIA GeForce RTX 5090 38; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash. On the models both run fully in memory, the NVIDIA GeForce RTX 5090 is about 6.6× 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 5090 $10,300 at Amazon: the ASUS Ascent GX10 128GB is $2,001 cheaper.

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

ASUS Ascent GX10 128GB

$8,299

Amazon

Add to build
NVIDIA GeForce RTX 5090

$10,300

Amazon

Add to build

Specifications

SpecASUS Ascent GX10 128GBNVIDIA GeForce RTX 5090
ChipGB10 Grace Blackwell–
Memory bus256-bit512-bit
Memory bandwidth273 GB/s1,792 GB/s
FP16 compute62 TFLOPS209 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 5090
Memory–32 GB GDDR7
Board power–575 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 GeForce RTX 5090
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_035tok/sQ8_0
Qwen 3.5 122B-A10B11tok/sQ6_Koffload
Qwen 3.6 27B6tok/sQ8_036tok/sQ8_0
gpt-oss 120B23tok/sMXFP4won't run
Qwen3 Coder Next20tok/sQ8_0offload
Nemotron 3 Super 120B-A12B9tok/sUD-Q6_Koffload
Gemma 4 31B5tok/sQ8_039tok/sQ6_K
Mistral Small 4 119B15tok/sUD-Q6_Koffload
Qwen 3.6 35B-A3B27tok/sQ8_0201tok/sQ6_K
Qwen 3.5 27B6tok/sQ8_036tok/sQ8_0
Gemma 4 26B-A4B20tok/sQ8_0132tok/sQ8_0
GLM 4.5 Air4tok/sQ8_0offload
Qwen 3.5 35B-A3B27tok/sQ8_0212tok/sQ6_K
Qwen3 Next 80B-A3B25tok/sQ8_0offload
GLM 4.7 Flash14tok/sQ8_0114tok/sQ6_K
Devstral Small 2 24B6tok/sQ8_037tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3B28tok/sUD-Q6_K_XLoffload
gpt-oss 20B31tok/sMXFP4206tok/sMXFP4
Kimi Linear 48B-A3B29tok/sQ8_0311tok/sQ4_K_M
Qwen3 Coder 30B-A3B16tok/sQ8_0117tok/sQ6_K
Qwen3 32B4tok/sQ8_035tok/sQ5_K_M
Gemma 4 12B13tok/sQ8_082tok/sQ8_0
Qwen 3.5 9B16tok/sQ8_0104tok/sQ8_0
Mistral Small 3.2 24B6tok/sQ8_037tok/sQ8_0
Gemma 3 27B5tok/sQ8_035tok/sQ8_0
DeepSeek R1 Distill Qwen 32B4tok/sQ8_035tok/sQ5_K_M
Llama 3.3 70B2tok/sQ8_0offload
Ministral 3 14B9tok/sQ8_056tok/sQ8_0
Qwen3 14B8tok/sQ8_053tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B13tok/sQ8_082tok/sQ8_0
Qwen3 8B13tok/sQ8_082tok/sQ8_0
Phi-4 14B8tok/sQ8_050tok/sQ8_0
Qwen 3.5 4B30tok/sQ8_0198tok/sQ8_0
Ministral 3 8B13tok/sQ8_082tok/sQ8_0
Granite 4.2 8B12tok/sQ8_076tok/sQ8_0
Gemma 4 E4B19tok/sQ8_0121tok/sQ8_0
LFM2.5 8B-A1B38tok/sQ8_0249tok/sQ8_0
Llama 3.1 8B16tok/sQ6_K102tok/sQ6_K
Qwen3.5 0.8B137tok/sQ8_0901tok/sQ8_0
Qwen3.5 2B100tok/sQ4_K_M657tok/sQ4_K_M
LFM2.5 2.6B35tok/sQ8_0227tok/sQ8_0
LFM2.5 VL 3B35tok/sQ8_0227tok/sQ8_0
granite 4.2 3b26tok/sQ8_0169tok/sQ8_0
LFM2.5 24B A2B21tok/sQ8_0139tok/sQ8_0
GLM 4.6V Flash15tok/sQ8_098tok/sQ8_0
Ministral 3 8B Reasoning 251213tok/sQ8_082tok/sQ8_0
GLM 4.5V5tok/sQ8_0won't run
GLM 4.6V5tok/sQ8_0won't run
granite 4.2 30b4tok/sQ8_038tok/sQ5_K_M
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 5.3won't runwon't run

Questions

Which is better for local AI, the ASUS Ascent GX10 128GB or the NVIDIA GeForce RTX 5090?
Choose the ASUS Ascent GX10 128GB to run bigger models. Choose the NVIDIA GeForce RTX 5090 for speed. Choose the ASUS Ascent GX10 128GB to spend less.
Which can run bigger models, the ASUS Ascent GX10 128GB or the NVIDIA GeForce RTX 5090?
At 32k context the ASUS Ascent GX10 128GB runs 53 of the models we track fully in memory and the NVIDIA GeForce RTX 5090 38; 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 5090?
On the models both run fully in memory, the NVIDIA GeForce RTX 5090 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 GeForce RTX 5090?
In Canada the ASUS Ascent GX10 128GB costs $8,299 at Amazon and the NVIDIA GeForce RTX 5090 $10,300 at Amazon: the ASUS Ascent GX10 128GB is $2,001 cheaper.

More comparisons