AMD Radeon AI PRO R9700
32 GB · 640 GB/s · 300 W
Prices
Every retailer we track in the US, 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 |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q6_K | fits | 25.8 GB | 143k250k with q8 cache | 13tok/sest. | 977 tok/s | chat |
| Qwen 3.6 27B Alibaba Qwen | Q6_K | fits | 26.3 GB | 135k237k with q8 cache | 13tok/sest. | 977 tok/s | chat |
| Gemma 4 31B | Q6_K | fits | 30.4 GB | 73k137k with q8 cache | 11tok/sest. | 892 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q6_K | fits | 29.8 GB | 119k187k with q8 cache | 55tok/sest. | 5880 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q6_K | fits | 26.2 GB | 136k239k with q8 cache | 13tok/sest. | 977 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.6 GB | 204k256k with q8 cache | 37tok/sest. | 6021 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 29.4 GB | 136k213k with q8 cache | 55tok/sest. | 5880 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q6_K | fits | 27.5 GB | 128k198k with q8 cache | 28tok/sest. | 2917 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q6_K | fits | 29.2 GB | 76k139k with q8 cache | 12tok/sest. | 962 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 29.7 GB | 174k237k with q8 cache | 88tok/sest. | 4723 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.0 GB | 128k | 52tok/sest. | 4500 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q6_K | fits | 30.5 GB | 70k126k with q8 cache | 24tok/sest. | 2104 tok/s | chat, coding, agents |
| Gemma 4 12B | Q8_0 | fits | 14.3 GB | 256k | 25tok/sest. | 2314 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.1 GB | 256k | 30tok/sest. | 2833 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q6_K | fits | 27.2 GB | 111k128k with q8 cache | 13tok/sest. | 1094 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q6_K | fits | 29.2 GB | 76k128k with q8 cache | 12tok/sest. | 962 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 24.5 GB | 105k191k with q8 cache | 14tok/sest. | 1354 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 25.8 GB | 40k | 13tok/sest. | 1186 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.3 GB | 128k | 19tok/sest. | 1872 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.3 GB | 40k | 19tok/sest. | 1872 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.2 GB | 16k | 12tok/sest. | 1190 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.4 GB | 256k | 53tok/sest. | 4910 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.1 GB | 158k256k with q8 cache | 19tok/sest. | 1852 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 19.9 GB | 128k | 18tok/sest. | 1712 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 10.6 GB | 128k | 35tok/sest. | 3710 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.6 GB | 125k | 49tok/sest. | 7918 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.3 GB | 128k | 23tok/sest. | 2011 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 41.8 GB | – | 17tok/sest. | 1715 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 47.9 GB | – | 18tok/sest. | 3699 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.7 GB | – | 11tok/sest. | 1771 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 40.0 GB | – | 24tok/sest. | 1726 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | offload | 54.9 GB | – | 3tok/sest. | 455 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 47.9 GB | – | 20tok/sest. | 4220 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.2 GB | – | 37tok/sest. | 6855 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 35.6 GB | 40k | 6tok/sest. | 460 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 35.7 GB | 46k85k with q8 cache | 6tok/sest. | 568 tok/s | chat |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 96.7 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.2 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.2 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 86.8 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 62.5 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 60.8 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