ASUS Ascent GX10 128GB vs Mac Studio M3 Ultra 96GB
For running models locally, priced in Germany. At 32k context the first runs 42 models fully in memory, the second 38.
In short
The ASUS Ascent GX10 128GB has more memory for models: 128 GB against 96 GB. At 32k context the ASUS Ascent GX10 128GB runs 42 of the models we track fully in memory and the Mac Studio M3 Ultra 96GB 38; only the ASUS Ascent GX10 128GB holds DeepSeek V4 Flash. On the models both run fully in memory, the Mac Studio M3 Ultra 96GB is about 3.1× as fast as the ASUS Ascent GX10 128GB (estimated, median across models). In Germany the ASUS Ascent GX10 128GB costs 8.623 € at eBay and the Mac Studio M3 Ultra 96GB 5.999 € at eBay: the Mac Studio M3 Ultra 96GB is 2.624 € cheaper.
Updated . Speeds are estimates; how they are worked out.
Specifications
| Spec | ASUS Ascent GX10 128GB | Mac Studio M3 Ultra 96GB |
|---|---|---|
| Chip | GB10 Grace Blackwell | Apple M3 Ultra (80-core GPU) |
| Memory bus | 256-bit | 1024-bit |
| Memory bandwidth | 273 GB/s | 819 GB/s |
| FP16 compute | 62 TFLOPS | 28 TFLOPS |
| Software | CUDA | Metal |
| Unified memory | 128 GB | 96 GB |
| GPU can use by default | 119 GB | 72 GB |
| GPU can use, tuned | 122 GB | 88 GB |
| Operating system | dgx-os | macos |
| Processor | 20-core Arm (GB10) | M3 Ultra 32-core |
| Storage | 1000 GB | 1000 GB |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | ASUS Ascent GX10 128GB | Mac Studio M3 Ultra 96GB |
|---|---|---|
| DeepSeek V4 Flash | 11tok/sUD-Q2_K_XL | won't run |
| GLM 5.3 Flash | 11tok/sUD-Q2_K_XL | won't run |
| Qwen 3.8 Flash Next | 3tok/sUD-Q4_K_XL | won't run |
| MiniMax M2.7 | 8tok/sUD-Q3_K_M | won't run |
| Qwen 3.8 27B | 5tok/sQ8_0 | 17tok/sQ8_0 |
| Qwen 3.5 122B-A10B | 11tok/sQ6_K | 58tok/sQ3_K_M |
| Qwen 3.6 27B | 6tok/sQ8_0 | 17tok/sQ8_0 |
| gpt-oss 120B | 23tok/sMXFP4 | 74tok/sMXFP4 |
| Qwen3 Coder Next | 20tok/sQ8_0 | 78tok/sQ6_K |
| Nemotron 3 Super 120B-A12B | 9tok/sUD-Q6_K | 50tok/sUD-Q3_K_M |
| Gemma 4 31B | 5tok/sQ8_0 | 15tok/sQ8_0 |
| Mistral Small 4 119B | 15tok/sUD-Q6_K | 62tok/sUD-Q4_K_M |
| Qwen 3.6 35B-A3B | 27tok/sQ8_0 | 84tok/sQ8_0 |
| Qwen 3.5 27B | 6tok/sQ8_0 | 17tok/sQ8_0 |
| Gemma 4 26B-A4B | 20tok/sQ8_0 | 63tok/sQ8_0 |
| GLM 4.5 Air | 4tok/sQ8_0 | 21tok/sQ3_K_M |
| Qwen 3.5 35B-A3B | 27tok/sQ8_0 | 84tok/sQ8_0 |
| Qwen3 Next 80B-A3B | 25tok/sQ8_0 | 97tok/sQ6_K |
| GLM 4.7 Flash | 14tok/sQ8_0 | 45tok/sQ8_0 |
| Devstral Small 2 24B | 6tok/sQ8_0 | 18tok/sQ8_0 |
| Nemotron 3.5 Lightning 30B-A3B | 28tok/sUD-Q6_K_XL | 89tok/sUD-Q6_K_XL |
| gpt-oss 20B | 31tok/sMXFP4 | 99tok/sMXFP4 |
| Kimi Linear 48B-A3B | 29tok/sQ8_0 | 91tok/sQ8_0 |
| Qwen3 Coder 30B-A3B | 16tok/sQ8_0 | 50tok/sQ8_0 |
| Qwen3 32B | 4tok/sQ8_0 | 12tok/sQ8_0 |
| Gemma 4 12B | 13tok/sQ8_0 | 39tok/sQ8_0 |
| Qwen 3.5 9B | 16tok/sQ8_0 | 50tok/sQ8_0 |
| Mistral Small 3.2 24B | 6tok/sQ8_0 | 18tok/sQ8_0 |
| Gemma 3 27B | 5tok/sQ8_0 | 17tok/sQ8_0 |
| DeepSeek R1 Distill Qwen 32B | 4tok/sQ8_0 | 12tok/sQ8_0 |
| Llama 3.3 70B | 2tok/sQ8_0 | 9tok/sQ5_K_M |
| Ministral 3 14B | 9tok/sQ8_0 | 27tok/sQ8_0 |
| Qwen3 14B | 8tok/sQ8_0 | 25tok/sQ8_0 |
| DeepSeek R1 0528 Qwen3 8B | 13tok/sQ8_0 | 39tok/sQ8_0 |
| Qwen3 8B | 13tok/sQ8_0 | 39tok/sQ8_0 |
| Phi-4 14B | 8tok/sQ8_0 | 24tok/sQ8_0 |
| Qwen 3.5 4B | 30tok/sQ8_0 | 95tok/sQ8_0 |
| Ministral 3 8B | 13tok/sQ8_0 | 39tok/sQ8_0 |
| Granite 4.2 8B | 12tok/sQ8_0 | 36tok/sQ8_0 |
| Gemma 4 E4B | 19tok/sQ8_0 | 58tok/sQ8_0 |
| LFM2.5 8B-A1B | 38tok/sQ8_0 | 119tok/sQ8_0 |
| Llama 3.1 8B | 16tok/sQ6_K | 49tok/sQ6_K |
Questions
- Which is better for local AI, the ASUS Ascent GX10 128GB or the Mac Studio M3 Ultra 96GB?
- Choose the ASUS Ascent GX10 128GB to run bigger models. Choose the Mac Studio M3 Ultra 96GB for speed. Choose the Mac Studio M3 Ultra 96GB to spend less.
- Which can run bigger models, the ASUS Ascent GX10 128GB or the Mac Studio M3 Ultra 96GB?
- At 32k context the ASUS Ascent GX10 128GB runs 42 of the models we track fully in memory and the Mac Studio M3 Ultra 96GB 38; 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 M3 Ultra 96GB?
- On the models both run fully in memory, the Mac Studio M3 Ultra 96GB is about 3.1× 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 M3 Ultra 96GB?
- In Germany the ASUS Ascent GX10 128GB costs 8.623 € at eBay and the Mac Studio M3 Ultra 96GB 5.999 € at eBay: the Mac Studio M3 Ultra 96GB is 2.624 € cheaper.
More comparisons
- ASUS Ascent GX10 128GB vs Framework Desktop Ryzen AI Max+ 395 128GB
- ASUS Ascent GX10 128GB vs GMKtec EVO-X2 Ryzen AI Max+ 395 128GB
- ASUS Ascent GX10 128GB vs Mac Studio M4 Max 128GB
- ASUS Ascent GX10 128GB vs NVIDIA DGX Spark 128GB
- ASUS Ascent GX10 128GB vs NVIDIA GeForce RTX 5090
- Mac Studio M3 Ultra 256GB vs Mac Studio M3 Ultra 96GB
- Mac Studio M3 Ultra 512GB vs Mac Studio M3 Ultra 96GB
- Mac Studio M3 Ultra 96GB vs Mac Studio M4 Max 128GB
- Mac Studio M3 Ultra 96GB vs Mac Studio M4 Max 64GB
- Mac Studio M3 Ultra 96GB vs NVIDIA DGX Spark 128GB