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 @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q6_K | fits | 30.2 GB | 143k250k with q8 cache | 12tok/sest. | 822 tok/s | chat |
| Qwen 3.6 27B Alibaba Qwen | Q6_K | fits | 30.7 GB | 135k237k with q8 cache | 11tok/sest. | 822 tok/s | chat |
| Gemma 4 31B | Q4_K_M | fits | 29.4 GB | 149k256k with q8 cache | 12tok/sest. | 780 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q5_K_M | fits | 28.7 GB | 224k256k with q8 cache | 43tok/sest. | 3994 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q6_K | fits | 30.6 GB | 136k239k with q8 cache | 11tok/sest. | 822 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.3 GB | 204k256k with q8 cache | 30tok/sest. | 4848 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 31.0 GB | 136k213k with q8 cache | 41tok/sest. | 3994 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q6_K | fits | 31.2 GB | 128k198k with q8 cache | 19tok/sest. | 1884 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 30.6 GB | 174k237k with q8 cache | 72tok/sest. | 2997 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 15.8 GB | 128k | 37tok/sest. | 3139 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | fits | 30.8 GB | 131k235k with q8 cache | 14tok/sest. | 1162 tok/s | chat, coding, agents |
| Gemma 4 12B | Q8_0 | fits | 15.7 GB | 256k | 23tok/sest. | 2015 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 14.5 GB | 256k | 25tok/sest. | 2396 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q5_K_M | fits | 29.9 GB | 128k | 12tok/sest. | 1006 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q4_K_M | fits | 29.9 GB | 40k | 12tok/sest. | 803 tok/s | chat, coding |
| Ministral 3 14B Mistral AI | Q5_K_M | fits | 30.5 GB | 132k241k with q8 cache | 11tok/sest. | 944 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 27.7 GB | 128k | 13tok/sest. | 1215 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 27.7 GB | 40k | 13tok/sest. | 1215 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 9.8 GB | 256k | 40tok/sest. | 3733 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 27.0 GB | 158k256k with q8 cache | 13tok/sest. | 1230 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 30.3 GB | 128k | 11tok/sest. | 1104 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 12.7 GB | 128k | 29tok/sest. | 3360 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 15.9 GB | 125k | 28tok/sest. | 4491 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 23.7 GB | 128k | 15tok/sest. | 1326 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 43.7 GB | – | 12tok/sest. | 1201 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 49.8 GB | – | 12tok/sest. | 2490 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 53.6 GB | – | 10tok/sest. | 1522 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 41.8 GB | – | 16tok/sest. | 1067 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 49.8 GB | – | 13tok/sest. | 2721 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 34.9 GB | 105k191k with q8 cache | 6tok/sest. | 686 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.9 GB | – | 31tok/sest. | 5011 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 52.0 GB | 40k | 2tok/sest. | 248 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 34.9 GB | 105k128k with q8 cache | 6tok/sest. | 686 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 52.0 GB | 46k85k with q8 cache | 2tok/sest. | 332 tok/s | chat |
| Phi-4 14B Microsoft | Q4_K_M | offload | 34.8 GB | 16k | 6tok/sest. | 753 tok/s | chat, coding |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 102.5 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 104.3 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 78.1 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 102.7 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 65.1 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 66.8 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 81.2 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