ASUS Ascent GX10 128GB
128 GB unified · 273 GB/s
Prices
Every retailer we track in Germany, cheapest first. Buy links may earn us a commission.
No retailer in this market lists it right now.
What it runs
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | fits | 96.6 GB | 312k557k with q8 cache | 8tok/sest. | 124 tok/s | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | fits | 103.1 GB | 1018k1024k with q8 cache | 11tok/sest. | 189 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q4_K_XL | fits | 106.4 GB | 256k | 3tok/sest. | 210 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 32.3 GB | 256k | 5tok/sest. | 408 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q3_K_M | fits | 110.9 GB | 96k178k with q8 cache | 5tok/sest. | 388 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q6_K | fits | 96.8 GB | 256k | 10tok/sest. | 848 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 31.8 GB | 256k | 5tok/sest. | 408 tok/s | – |
| gpt-oss 120B OpenAI | MXFP4 | fits | 62.4 GB | 128k | 18tok/sest. | 1316 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q8_0 | fits | 81.6 GB | 256k | 18tok/sest. | 1966 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q6_K | fits | 108.6 GB | 256k | 9tok/sest. | 986 tok/s | – |
| Gemma 4 31B | Q8_0 | fits | 37.3 GB | 256k | 4tok/sest. | 372 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q6_K | fits | 95.1 GB | 923k1024k with q8 cache | 14tok/sest. | 834 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 23tok/sest. | 2454 tok/s | chat, coding, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 31.8 GB | 256k | 5tok/sest. | 408 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.5 GB | 256k | 18tok/sest. | 2513 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q6_K | fits | 104.8 GB | 128k | 4tok/sest. | 258 tok/s | – |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 23tok/sest. | 2454 tok/s | chat, coding, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q8_0 | fits | 81.6 GB | 256k | 21tok/sest. | 2242 tok/s | chat, coding, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 34.0 GB | 198k | 12tok/sest. | 1217 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 34.4 GB | 384k | 5tok/sest. | 402 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.1 GB | 256k | 27tok/sest. | 3026 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 50.3 GB | 1024k | 27tok/sest. | 1971 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.9 GB | 128k | 25tok/sest. | 1878 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 37.3 GB | 256k | 11tok/sest. | 878 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 49.5 GB | 40k | 3tok/sest. | 208 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 14.2 GB | 256k | 12tok/sest. | 966 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.0 GB | 256k | 14tok/sest. | 1182 tok/s | chat |
| Gemma 3 27B | Q8_0 | fits | 33.2 GB | 128k | 5tok/sest. | 457 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 34.4 GB | 128k | 5tok/sest. | 402 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 49.5 GB | 128k | 3tok/sest. | 257 tok/s | – |
| Llama 3.3 70B Meta | Q8_0 | fits | 90.9 GB | 128k | 2tok/sest. | 123 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 24.4 GB | 256k | 7tok/sest. | 565 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 25.7 GB | 40k | 6tok/sest. | 495 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.2 GB | 128k | 9tok/sest. | 781 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.2 GB | 40k | 9tok/sest. | 781 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.1 GB | 16k | 6tok/sest. | 497 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.3 GB | 256k | 25tok/sest. | 2049 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.0 GB | 256k | 9tok/sest. | 773 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 19.8 GB | 128k | 8tok/sest. | 714 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 10.5 GB | 128k | 17tok/sest. | 1548 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.5 GB | 125k | 24tok/sest. | 3305 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 15.2 GB | 128k | 11tok/sest. | 839 tok/s | chat |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- Chip
- GB10 Grace Blackwell
- Memory bus
- 256-bit
- Memory bandwidth
- 273 GB/s
- FP16 compute
- 62 TFLOPS
- Software
- CUDA
- Unified memory
- 128 GB
- GPU can use by default
- 119 GB
- GPU can use, tuned
- 122 GB
- Operating system
- dgx-os
- Processor
- 20-core Arm (GB10)
- Storage
- 1000 GB