readygpu

ASUS Ascent GX10 128GB vs Framework Desktop Ryzen AI Max+ 395 64GB

For running models locally, priced in Canada. At 8k context the first runs 80 models fully in memory, the second 68.

In short

The ASUS Ascent GX10 128GB has more memory for models: 128 GB against 64 GB. At 8k context the ASUS Ascent GX10 128GB runs 80 of the models we track fully in memory and the Framework Desktop Ryzen AI Max+ 395 64GB 68; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash. On the models both run fully in memory, the ASUS Ascent GX10 128GB is about 1.2× as fast as the Framework Desktop Ryzen AI Max+ 395 64GB (estimated, median across models).

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

ASUS Ascent GX10 128GB

$8,299

Amazon

Add to build
Framework Desktop Ryzen AI Max+ 395 64GB

Not priced here

Add to build

Specifications

SpecASUS Ascent GX10 128GBFramework Desktop Ryzen AI Max+ 395 64GB
ChipGB10 Grace BlackwellRyzen AI Max+ 395 (Radeon 8060S)
Memory bus256-bit256-bit
Memory bandwidth273 GB/s256 GB/s
FP16 compute62 TFLOPS59.4 TFLOPS
SoftwareCUDAROCm
Unified memory128 GB64 GB
GPU can use by default119 GB48 GB
GPU can use, tuned122 GB56 GB
Operating systemdgx-oslinux
Processor20-core Arm (GB10)Ryzen AI Max+ 395
Storage1000 GB1000 GB

What each runs

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

ModelASUS Ascent GX10 128GBFramework Desktop Ryzen AI Max+ 395 64GB
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_05tok/sQ8_0
Qwen 3.5 122B-A10B12tok/sQ6_K23tok/sUD-Q2_K_XL
Qwen 3.6 27B6tok/sQ8_05tok/sQ8_0
gpt-oss 120B30tok/sMXFP4won't run
Qwen3 Coder Next23tok/sQ8_032tok/sQ4_K_M
Nemotron 3 Super 120B-A12B9tok/sUD-Q6_Kwon't run
Gemma 4 31B5tok/sQ8_04tok/sQ8_0
Mistral Small 4 119B13tok/sQ8_033tok/sUD-Q2_K_XL
Qwen 3.6 35B-A3B31tok/sQ8_026tok/sQ8_0
Qwen 3.5 27B6tok/sQ8_05tok/sQ8_0
Gemma 4 26B-A4B22tok/sQ8_019tok/sQ8_0
GLM 4.5 Air6tok/sQ8_012tok/sQ2_K
Qwen 3.5 35B-A3B31tok/sQ8_026tok/sQ8_0
Qwen3 Next 80B-A3B30tok/sQ8_041tok/sQ4_K_M
GLM 4.7 Flash18tok/sQ8_015tok/sQ8_0
Devstral Small 2 24B6tok/sQ8_05tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3B30tok/sUD-Q6_K_XL25tok/sUD-Q6_K_XL
gpt-oss 20B39tok/sMXFP432tok/sMXFP4
Kimi Linear 48B-A3B31tok/sQ8_033tok/sQ6_K
Qwen3 Coder 30B-A3B25tok/sQ8_021tok/sQ8_0
Qwen3 32B5tok/sQ8_04tok/sQ8_0
Gemma 4 12B13tok/sQ8_011tok/sQ8_0
Qwen 3.5 9B17tok/sQ8_014tok/sQ8_0
Mistral Small 3.2 24B6tok/sQ8_05tok/sQ8_0
Gemma 3 27B6tok/sQ8_05tok/sQ8_0
DeepSeek R1 Distill Qwen 32B5tok/sQ8_04tok/sQ8_0
Llama 3.3 70B2tok/sQ8_03tok/sQ4_K_M
Ministral 3 14B11tok/sQ8_09tok/sQ8_0
Qwen3 14B10tok/sQ8_08tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B17tok/sQ8_014tok/sQ8_0
Qwen3 8B17tok/sQ8_014tok/sQ8_0
Phi-4 14B10tok/sQ8_08tok/sQ8_0
Qwen 3.5 4B35tok/sQ8_029tok/sQ8_0
Ministral 3 8B17tok/sQ8_014tok/sQ8_0
Granite 4.2 8B16tok/sQ8_013tok/sQ8_0
Gemma 4 E4B20tok/sQ8_017tok/sQ8_0
LFM2.5 8B-A1B69tok/sQ8_058tok/sQ8_0
Llama 3.1 8B22tok/sQ6_K18tok/sQ6_K
Qwen2.5 0.5B268tok/sQ8_0223tok/sQ8_0
Qwen3.5 0.8B182tok/sQ8_0151tok/sQ8_0
Qwen3.5 2B109tok/sQ5_K_M91tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B80tok/sQ8_066tok/sQ8_0
MiniCPM5 2B56tok/sQ8_046tok/sQ8_0
LFM2.5 2.6B50tok/sQ8_042tok/sQ8_0
LFM2.5 VL 3B50tok/sQ8_042tok/sQ8_0
Spark X2.5 4B50tok/smlx-4bit41tok/smlx-4bit
granite vision 4.1 4b39tok/sQ8_033tok/sQ8_0
Ministral 3 3B Instruct 251237tok/sQ8_031tok/sQ8_0
granite 4.2 3b37tok/sQ8_031tok/sQ8_0
LFM2.5 24B A2B36tok/sQ8_030tok/sQ8_0
Mellum2.1 12B A2.5B Thinking36tok/sQ8_030tok/sQ8_0
FrogNano 4B 260934tok/sQ8_029tok/sQ8_0
Kimi VL A3B Thinking 250630tok/sQ8_025tok/sQ8_0
Kimi VL A3B29tok/smlx-8bit24tok/smlx-8bit
DeepSeek R1 Distill Qwen 7B20tok/sQ8_016tok/sQ8_0
GLM 4 9B 041420tok/smlx-5bit16tok/smlx-5bit
DeepSeek R1 Distill Llama 8B18tok/sQ8_015tok/sQ8_0
Ministral 3 8B Reasoning 251217tok/sQ8_014tok/sQ8_0
GLM 4.6V Flash16tok/sQ8_014tok/sQ8_0
GLM 4.1V 9B Thinking14tok/smlx-8bit12tok/smlx-8bit
MiniMax M2.513tok/sMXFP4won't run
Ministral 3 14B Reasoning 251211tok/sQ8_09tok/sQ8_0
DeepSeek R1 Distill Qwen 14B10tok/sQ8_08tok/sQ8_0
Qwen3.8 27B OBLITERATED8tok/smlx-4bit7tok/smlx-4bit
Devstral Small 25076tok/sQ8_05tok/sQ8_0
Magistral Small 25066tok/sQ8_05tok/sQ8_0
Magistral Small 25076tok/sQ8_05tok/sQ8_0
Magistral Small 25096tok/sQ8_05tok/sQ8_0
GLM 4.5V6tok/sQ8_0won't run
GLM 4.6V6tok/sQ8_0won't run
Muse Glimmer 30B5tok/sQ8_04tok/sQ8_0
granite 4.2 30b5tok/sQ8_04tok/sQ8_0
DeepSeek R1 Distill Llama 70B2tok/sQ8_03tok/sQ4_K_M
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 Framework Desktop Ryzen AI Max+ 395 64GB?
Choose the ASUS Ascent GX10 128GB to run bigger models. Choose the ASUS Ascent GX10 128GB for speed.
Which can run bigger models, the ASUS Ascent GX10 128GB or the Framework Desktop Ryzen AI Max+ 395 64GB?
At 8k context the ASUS Ascent GX10 128GB runs 80 of the models we track fully in memory and the Framework Desktop Ryzen AI Max+ 395 64GB 68; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash.
Which is faster for local AI, the ASUS Ascent GX10 128GB or the Framework Desktop Ryzen AI Max+ 395 64GB?
On the models both run fully in memory, the ASUS Ascent GX10 128GB is about 1.2× as fast as the Framework Desktop Ryzen AI Max+ 395 64GB (estimated, median across models).

More comparisons

More hardware for local AI