readygpu

ASUS Ascent GX10 128GB vs NVIDIA GeForce RTX 5080

For running models locally, priced in Canada. At 8k context the first runs 81 models fully in memory, the second 44.

In short

The ASUS Ascent GX10 128GB has more memory for models: 128 GB against 16 GB. At 8k context the ASUS Ascent GX10 128GB runs 81 of the models we track fully in memory and the NVIDIA GeForce RTX 5080 44; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash. On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 3.5× as fast as the ASUS Ascent GX10 128GB (estimated, median across models). In Canada the ASUS Ascent GX10 128GB costs $8,500 at eBay (used) and the NVIDIA GeForce RTX 5080 $7,000 at eBay: the NVIDIA GeForce RTX 5080 is $1,500 cheaper.

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

ASUS Ascent GX10 128GB

$8,500

eBay, used (asking)

Add to build
NVIDIA GeForce RTX 5080

$7,000

eBay

Add to build

Specifications

SpecASUS Ascent GX10 128GBNVIDIA GeForce RTX 5080
ChipGB10 Grace Blackwell–
Memory bus256-bit256-bit
Memory bandwidth273 GB/s960 GB/s
FP16 compute62 TFLOPS113 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 5080
Memory–16 GB GDDR7
Board power–360 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 5080
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_0offload
Qwen 3.5 122B-A10B12tok/sQ6_Koffload
Qwen 3.6 27B6tok/sQ8_0offload
gpt-oss 120B30tok/sMXFP4won't run
Qwen3 Coder Next23tok/sQ8_0won't run
Nemotron 3 Super 120B-A12B9tok/sUD-Q6_Kwon't run
Gemma 4 31B5tok/sQ8_0offload
Mistral Small 4 119B13tok/sQ8_0offload
Qwen 3.6 35B-A3B31tok/sQ8_0offload
Qwen 3.5 27B6tok/sQ8_0offload
Gemma 4 26B-A4B22tok/sQ8_0offload
GLM 4.5 Air6tok/sQ8_0won't run
Qwen 3.5 35B-A3B31tok/sQ8_0offload
Qwen3 Next 80B-A3B30tok/sQ8_0won't run
GLM 4.7 Flash18tok/sQ8_0offload
Devstral Small 2 24B6tok/sQ8_038tok/sQ4_K_M
Nemotron 3.5 Lightning 30B-A3B30tok/sUD-Q6_K_XLoffload
gpt-oss 20B39tok/sMXFP4136tok/sMXFP4
Kimi Linear 48B-A3B31tok/sQ8_0offload
Qwen3 Coder 30B-A3B25tok/sQ8_0offload
Qwen3 32B5tok/sQ8_0offload
Gemma 4 12B13tok/sQ8_045tok/sQ8_0
Qwen 3.5 9B17tok/sQ8_060tok/sQ8_0
Mistral Small 3.2 24B6tok/sQ8_038tok/sQ4_K_M
Gemma 3 27B6tok/sQ8_0offload
DeepSeek R1 Distill Qwen 32B5tok/sQ8_0offload
Llama 3.3 70B2tok/sQ8_0won't run
Ministral 3 14B11tok/sQ8_038tok/sQ8_0
Qwen3 14B10tok/sQ8_044tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B17tok/sQ8_060tok/sQ8_0
Qwen3 8B17tok/sQ8_060tok/sQ8_0
Phi-4 14B10tok/sQ8_043tok/sQ6_K
Qwen 3.5 4B35tok/sQ8_0124tok/sQ8_0
Ministral 3 8B17tok/sQ8_059tok/sQ8_0
Granite 4.2 8B16tok/sQ8_056tok/sQ8_0
Gemma 4 E4B20tok/sQ8_070tok/sQ8_0
LFM2.5 8B-A1B69tok/sQ8_0244tok/sQ8_0
Llama 3.1 8B22tok/sQ6_K78tok/sQ6_K
Qwen2.5 0.5B268tok/sQ8_0942tok/sQ8_0
Qwen3.5 0.8B182tok/sQ8_0639tok/sQ8_0
Qwen3.5 2B109tok/sQ5_K_M383tok/sQ5_K_M
LFM3 1.7B87tok/sQ8_0304tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B80tok/sQ8_0280tok/sQ8_0
MiniCPM5 2B56tok/sQ8_0196tok/sQ8_0
LFM2.5 2.6B50tok/sQ8_0176tok/sQ8_0
LFM2.5 VL 3B50tok/sQ8_0176tok/sQ8_0
Spark X2.5 4B50tok/smlx-4bit175tok/smlx-4bit
granite vision 4.1 4b39tok/sQ8_0139tok/sQ8_0
Ministral 3 3B Instruct 251237tok/sQ8_0132tok/sQ8_0
granite 4.2 3b37tok/sQ8_0130tok/sQ8_0
LFM2.5 24B A2B36tok/sQ8_0offload
Mellum2.1 12B A2.5B Thinking36tok/sQ8_0127tok/sQ8_0
FrogNano 4B 260934tok/sQ8_0121tok/sQ8_0
Kimi VL A3B Thinking 250630tok/sQ8_0164tok/sQ4_K_M
Kimi VL A3B29tok/smlx-8bit128tok/smlx-6bit
DeepSeek R1 Distill Qwen 7B20tok/sQ8_070tok/sQ8_0
GLM 4 9B 041420tok/smlx-5bit69tok/smlx-5bit
DeepSeek R1 Distill Llama 8B18tok/sQ8_062tok/sQ8_0
Ministral 3 8B Reasoning 251217tok/sQ8_059tok/sQ8_0
GLM 4.6V Flash16tok/sQ8_058tok/sQ8_0
GLM 4.1V 9B Thinking14tok/smlx-8bit49tok/smlx-8bit
MiniMax M2.513tok/sMXFP4won't run
Ministral 3 14B Reasoning 251211tok/sQ8_038tok/sQ8_0
DeepSeek R1 Distill Qwen 14B10tok/sQ8_043tok/sQ6_K
Qwen3.8 27B OBLITERATED8tok/smlx-4bitoffload
Devstral Small 25076tok/sQ8_038tok/sQ4_K_M
Magistral Small 25066tok/sQ8_038tok/sQ4_K_M
Magistral Small 25076tok/sQ8_038tok/sQ4_K_M
Magistral Small 25096tok/sQ8_038tok/sQ4_K_M
GLM 4.5V6tok/sQ8_0won't run
GLM 4.6V6tok/sQ8_0won't run
Muse Glimmer 30B5tok/sQ8_0offload
granite 4.2 30b5tok/sQ8_0offload
DeepSeek R1 Distill Llama 70B2tok/sQ8_0won't run
Kimi Dev 72B2tok/sQ8_0won't run
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 M3won't runwon't run

Questions

Which is better for local AI, the ASUS Ascent GX10 128GB or the NVIDIA GeForce RTX 5080?
Choose the ASUS Ascent GX10 128GB to run bigger models. Choose the NVIDIA GeForce RTX 5080 for speed. Choose the NVIDIA GeForce RTX 5080 to spend less.
Which can run bigger models, the ASUS Ascent GX10 128GB or the NVIDIA GeForce RTX 5080?
At 8k context the ASUS Ascent GX10 128GB runs 81 of the models we track fully in memory and the NVIDIA GeForce RTX 5080 44; 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 5080?
On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 3.5× 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 5080?
In Canada the ASUS Ascent GX10 128GB costs $8,500 at eBay (used) and the NVIDIA GeForce RTX 5080 $7,000 at eBay: the NVIDIA GeForce RTX 5080 is $1,500 cheaper.

More comparisons

More hardware for local AI