readygpu

ASUS Ascent GX10 128GB vs Mac Studio M4 Max 64GB

For running models locally, priced in the UK. At 32k context the first runs 69 models fully in memory, the second 57.

In short

The ASUS Ascent GX10 128GB has more memory for models: 128 GB against 64 GB. At 32k context the ASUS Ascent GX10 128GB runs 69 of the models we track fully in memory and the Mac Studio M4 Max 64GB 57; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash. On the models both run fully in memory, the Mac Studio M4 Max 64GB is about 2.1× as fast as the ASUS Ascent GX10 128GB (estimated, median across models). In the UK the ASUS Ascent GX10 128GB costs £4,500 at Amazon and the Mac Studio M4 Max 64GB £3,399 at eBay: the Mac Studio M4 Max 64GB is £1,101 cheaper.

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

ASUS Ascent GX10 128GB

£4,500

Amazon

Add to build
Mac Studio M4 Max 64GB

£3,399

eBay

Add to build

Specifications

SpecASUS Ascent GX10 128GBMac Studio M4 Max 64GB
ChipGB10 Grace BlackwellApple M4 Max (40-core GPU)
Memory bus256-bit512-bit
Memory bandwidth273 GB/s546 GB/s
FP16 compute62 TFLOPS16.16 TFLOPS
SoftwareCUDAMetal
Unified memory128 GB64 GB
GPU can use by default119 GB48 GB
GPU can use, tuned122 GB56 GB
Operating systemdgx-osmacos
Processor20-core Arm (GB10)M4 Max 16-core
Storage1000 GB1000 GB

What each runs

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

ModelASUS Ascent GX10 128GBMac Studio M4 Max 64GB
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_011tok/sQ8_0
Qwen 3.5 122B-A10B11tok/sQ6_K50tok/sUD-Q2_K_XL
Qwen 3.6 27B6tok/sQ8_012tok/sQ8_0
gpt-oss 120B23tok/sMXFP4won't run
Qwen3 Coder Next20tok/sQ8_066tok/sQ4_K_M
Nemotron 3 Super 120B-A12B9tok/sUD-Q6_Kwon't run
Gemma 4 31B5tok/sQ8_010tok/sQ8_0
Mistral Small 4 119B15tok/sUD-Q6_K68tok/sUD-Q2_K_XL
Qwen 3.6 35B-A3B27tok/sQ8_056tok/sQ8_0
Qwen 3.5 27B6tok/sQ8_012tok/sQ8_0
Gemma 4 26B-A4B20tok/sQ8_042tok/sQ8_0
GLM 4.5 Air4tok/sQ8_0won't run
Qwen 3.5 35B-A3B27tok/sQ8_056tok/sQ8_0
Qwen3 Next 80B-A3B25tok/sQ8_080tok/sQ4_K_M
GLM 4.7 Flash14tok/sQ8_030tok/sQ8_0
Devstral Small 2 24B6tok/sQ8_012tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3B28tok/sUD-Q6_K_XL60tok/sUD-Q6_K_XL
gpt-oss 20B31tok/sMXFP466tok/sMXFP4
Kimi Linear 48B-A3B29tok/sQ8_077tok/sQ6_K
Qwen3 Coder 30B-A3B16tok/sQ8_033tok/sQ8_0
Qwen3 32B4tok/sQ8_08tok/sQ8_0
Gemma 4 12B13tok/sQ8_026tok/sQ8_0
Qwen 3.5 9B16tok/sQ8_033tok/sQ8_0
Mistral Small 3.2 24B6tok/sQ8_012tok/sQ8_0
Gemma 3 27B5tok/sQ8_011tok/sQ8_0
DeepSeek R1 Distill Qwen 32B4tok/sQ8_08tok/sQ8_0
Llama 3.3 70B2tok/sQ8_0won't run
Ministral 3 14B9tok/sQ8_018tok/sQ8_0
Qwen3 14B8tok/sQ8_017tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B13tok/sQ8_026tok/sQ8_0
Qwen3 8B13tok/sQ8_026tok/sQ8_0
Phi-4 14B8tok/sQ8_016tok/sQ8_0
Qwen 3.5 4B30tok/sQ8_063tok/sQ8_0
Ministral 3 8B13tok/sQ8_026tok/sQ8_0
Granite 4.2 8B12tok/sQ8_024tok/sQ8_0
Gemma 4 E4B19tok/sQ8_039tok/sQ8_0
LFM2.5 8B-A1B38tok/sQ8_080tok/sQ8_0
Llama 3.1 8B16tok/sQ6_K33tok/sQ6_K
Qwen2.5 0.5B181tok/sQ8_0380tok/sQ8_0
Qwen3.5 0.8B137tok/sQ8_0288tok/sQ8_0
Qwen3.5 2B91tok/sQ5_K_M191tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B60tok/sQ8_0125tok/sQ8_0
MiniCPM5 2B41tok/sQ8_087tok/sQ8_0
LFM2.5 2.6B35tok/sQ8_073tok/sQ8_0
LFM2.5 VL 3B35tok/sQ8_073tok/sQ8_0
Mellum2.1 12B A2.5B Thinking32tok/sQ8_067tok/sQ8_0
granite vision 4.1 4b27tok/sQ8_056tok/sQ8_0
granite 4.2 3b26tok/sQ8_054tok/sQ8_0
Kimi VL A3B24tok/smlx-8bit50tok/smlx-8bit
LFM2.5 24B A2B21tok/sQ8_044tok/sQ8_0
DeepSeek R1 Distill Qwen 7B17tok/sQ8_036tok/sQ8_0
GLM 4.6V Flash15tok/sQ8_031tok/sQ8_0
DeepSeek R1 Distill Llama 8B13tok/sQ8_028tok/sQ8_0
GLM 4.1V 9B Thinking13tok/smlx-8bit27tok/smlx-8bit
Ministral 3 8B Reasoning 251213tok/sQ8_026tok/sQ8_0
DeepSeek R1 Distill Qwen 14B8tok/sQ8_016tok/sQ8_0
Devstral Small 25076tok/sQ8_012tok/sQ8_0
Magistral Small 25066tok/sQ8_012tok/sQ8_0
Magistral Small 25076tok/sQ8_012tok/sQ8_0
Magistral Small 25096tok/sQ8_012tok/sQ8_0
GLM 4.5V5tok/sQ8_0won't run
GLM 4.6V5tok/sQ8_0won't run
granite 4.2 30b4tok/sQ8_09tok/sQ8_0
DeepSeek R1 Distill Llama 70B2tok/sQ8_0won'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 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 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 Mac Studio M4 Max 64GB?
Choose the ASUS Ascent GX10 128GB to run bigger models. Choose the Mac Studio M4 Max 64GB for speed. Choose the Mac Studio M4 Max 64GB to spend less.
Which can run bigger models, the ASUS Ascent GX10 128GB or the Mac Studio M4 Max 64GB?
At 32k context the ASUS Ascent GX10 128GB runs 69 of the models we track fully in memory and the Mac Studio M4 Max 64GB 57; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash.
Which is faster for local AI, the ASUS Ascent GX10 128GB or the Mac Studio M4 Max 64GB?
On the models both run fully in memory, the Mac Studio M4 Max 64GB is about 2.1× 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 Mac Studio M4 Max 64GB?
In the UK the ASUS Ascent GX10 128GB costs £4,500 at Amazon and the Mac Studio M4 Max 64GB £3,399 at eBay: the Mac Studio M4 Max 64GB is £1,101 cheaper.

More comparisons