AMD Radeon AI PRO R9700
32 GB · 640 GB/s · 300 W
Prices
Every retailer we track in the UK, 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 @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 37.2 GB | 256k | 9tok/sest. | 822 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q3_K_M | fits | 57.7 GB | 256k | 27tok/sest. | 1461 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 9tok/sest. | 822 tok/s | – |
| Qwen3 Coder Next Alibaba Qwen | Q5_K_M | fits | 58.1 GB | 256k | 35tok/sest. | 3240 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q3_K_M | fits | 60.7 GB | 253k256k with q8 cache | 29tok/sest. | 2051 tok/s | chat, coding, agents, long documents |
| Gemma 4 31B | Q8_0 | fits | 43.2 GB | 256k | 8tok/sest. | 780 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q3_K_M | fits | 55.5 GB | 375k596k with q8 cache | 34tok/sest. | 1267 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 39.0 GB | 256k | 36tok/sest. | 3994 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 9tok/sest. | 822 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.8 GB | 256k | 30tok/sest. | 4848 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q5_K_M | fits | 58.0 GB | 256k | 39tok/sest. | 3540 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 39.0 GB | 256k | 36tok/sest. | 3994 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 38.3 GB | 198k | 17tok/sest. | 1884 tok/s | chat, coding, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 45.4 GB | 232k384k with q8 cache | 8tok/sest. | 735 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 35.4 GB | 256k | 51tok/sest. | 5373 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 51.7 GB | 915k1024k with q8 cache | 49tok/sest. | 2997 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 16.3 GB | 128k | 37tok/sest. | 3139 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 44.3 GB | 256k | 13tok/sest. | 1162 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q6_K | fits | 59.1 GB | 40k | 6tok/sest. | 329 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 16.2 GB | 256k | 23tok/sest. | 2015 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 15.0 GB | 256k | 25tok/sest. | 2396 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 39.2 GB | 128k | 9tok/sest. | 1006 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 45.4 GB | 128k | 8tok/sest. | 735 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q6_K | fits | 59.1 GB | 128k | 6tok/sest. | 442 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 35.4 GB | 256k | 10tok/sest. | 944 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 36.7 GB | 40k | 10tok/sest. | 803 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 28.2 GB | 128k | 13tok/sest. | 1215 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 28.2 GB | 40k | 13tok/sest. | 1215 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 41.6 GB | 16k | 8tok/sest. | 805 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 40tok/sest. | 3733 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 27.5 GB | 256k | 13tok/sest. | 1230 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 30.8 GB | 128k | 11tok/sest. | 1104 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 13.2 GB | 128k | 29tok/sest. | 3360 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 16.4 GB | 125k | 28tok/sest. | 4491 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 24.2 GB | 128k | 15tok/sest. | 1326 tok/s | chat, coding |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | offload | 78.6 GB | – | 3tok/sest. | 410 tok/s | – |
| gpt-oss 120B OpenAI | MXFP4 | offload | 65.6 GB | 50k84k with q8 cache | 21tok/sest. | 2101 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | offload | 67.3 GB | 101k128k with q8 cache | 5tok/sest. | 350 tok/s | chat |
| Llama 3.3 70B Meta | Q4_K_M | offload | 81.7 GB | 67k125k with q8 cache | 2tok/sest. | 183 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 103.0 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 104.8 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 103.2 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