AMD Radeon AI PRO R9700
32 GB · 640 GB/s · 300 W
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 two of them run
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 |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 32.9 GB | 256k | 11tok/sest. | 977 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q3_K_M | fits | 55.9 GB | 256k | 34tok/sest. | 2033 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 32.4 GB | 256k | 11tok/sest. | 977 tok/s | – |
| Qwen3 Coder Next Alibaba Qwen | Q5_K_M | fits | 56.2 GB | 256k | 48tok/sest. | 4710 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q3_K_M | fits | 59.8 GB | 253k256k with q8 cache | 32tok/sest. | 2363 tok/s | chat, coding, agents, long documents |
| Gemma 4 31B | Q8_0 | fits | 37.9 GB | 256k | 9tok/sest. | 892 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q3_K_M | fits | 53.7 GB | 375k596k with q8 cache | 45tok/sest. | 1999 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.4 GB | 256k | 47tok/sest. | 5880 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 32.4 GB | 256k | 11tok/sest. | 977 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 28.1 GB | 256k | 37tok/sest. | 6021 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | fits | 55.4 GB | 101k128k with q8 cache | 11tok/sest. | 618 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q5_K_M | fits | 56.2 GB | 256k | 56tok/sest. | 5373 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.4 GB | 256k | 47tok/sest. | 5880 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 34.6 GB | 198k | 24tok/sest. | 2917 tok/s | chat, coding, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 35.0 GB | 232k384k with q8 cache | 10tok/sest. | 962 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.7 GB | 256k | 56tok/sest. | 7250 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 50.9 GB | 915k1024k with q8 cache | 56tok/sest. | 4723 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.5 GB | 128k | 52tok/sest. | 4500 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 37.9 GB | 256k | 22tok/sest. | 2104 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 50.1 GB | 40k | 7tok/sest. | 498 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 14.8 GB | 256k | 25tok/sest. | 2314 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.6 GB | 256k | 30tok/sest. | 2833 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 33.8 GB | 128k | 10tok/sest. | 1094 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 35.0 GB | 128k | 10tok/sest. | 962 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 50.1 GB | 112k128k with q8 cache | 7tok/sest. | 616 tok/s | – |
| Llama 3.3 70B Meta | Q4_K_M | fits | 61.3 GB | 67k125k with q8 cache | 6tok/sest. | 295 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 25.0 GB | 256k | 14tok/sest. | 1354 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 26.3 GB | 40k | 13tok/sest. | 1186 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.8 GB | 128k | 19tok/sest. | 1872 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.8 GB | 40k | 19tok/sest. | 1872 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.7 GB | 16k | 12tok/sest. | 1190 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.9 GB | 256k | 53tok/sest. | 4910 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.6 GB | 256k | 19tok/sest. | 1852 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.4 GB | 128k | 18tok/sest. | 1712 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 11.1 GB | 128k | 35tok/sest. | 3710 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 13.1 GB | 125k | 49tok/sest. | 7918 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.8 GB | 128k | 23tok/sest. | 2011 tok/s | chat, coding |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | offload | 76.7 GB | – | 4tok/sest. | 446 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | offload | 87.3 GB | – | 4tok/sest. | 767 tok/s | chat |
| gpt-oss 120B OpenAI | MXFP4 | offload | 63.0 GB | 50k84k with q8 cache | 36tok/sest. | 3136 tok/s | chat, coding, agents, long documents |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 97.2 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.7 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- Radeon AI PRO R9700
- Memory
- 32 GB GDDR6
- Memory bus
- 256-bit
- Memory bandwidth
- 640 GB/s
- FP16 compute
- 191 TFLOPS
- Software
- ROCm
- Board power
- 300 W
- PCIe generation
- Gen 5
- PCIe lanes
- x16