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 it runs
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 30.2 GB | 46k82k with q8 cache | 11tok/sest. | 1078 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 29.8 GB | 53k92k with q8 cache | 11tok/sest. | 1078 tok/s | – |
| Gemma 4 31B | Q6_K | fits | 27.7 GB | 73k137k with q8 cache | 12tok/sest. | 961 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q6_K | fits | 29.0 GB | 119k187k with q8 cache | 66tok/sest. | 7698 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 29.8 GB | 53k92k with q8 cache | 11tok/sest. | 1078 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.8 GB | 204k256k with q8 cache | 42tok/sest. | 6848 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 28.5 GB | 136k213k with q8 cache | 67tok/sest. | 7698 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q6_K | fits | 25.6 GB | 128k198k with q8 cache | 36tok/sest. | 4019 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 29.3 GB | 43k79k with q8 cache | 12tok/sest. | 1138 tok/s | – |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 29.3 GB | 174k237k with q8 cache | 99tok/sest. | 6634 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.0 GB | 128k | 65tok/sest. | 5747 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q6_K | fits | 27.4 GB | 70k126k with q8 cache | 37tok/sest. | 3540 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q5_K_M | fits | 30.6 GB | 34k40k with q8 cache | 11tok/sest. | 669 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.6 GB | 256k | 26tok/sest. | 2500 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.9 GB | 256k | 33tok/sest. | 3116 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 29.3 GB | 43k79k with q8 cache | 12tok/sest. | 1138 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q5_K_M | fits | 30.7 GB | 34k62k with q8 cache | 11tok/sest. | 768 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 30.6 GB | 38k72k with q8 cache | 11tok/sest. | 1144 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 19.4 GB | 105k191k with q8 cache | 18tok/sest. | 1731 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 20.6 GB | 40k | 17tok/sest. | 1556 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.6 GB | 128k | 26tok/sest. | 2567 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.6 GB | 40k | 26tok/sest. | 2567 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 21.7 GB | 16k | 16tok/sest. | 1564 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.2 GB | 256k | 63tok/sest. | 5830 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.6 GB | 158k256k with q8 cache | 26tok/sest. | 2479 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 14.7 GB | 128k | 24tok/sest. | 2361 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 9.5 GB | 128k | 38tok/sest. | 3914 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.9 GB | 125k | 79tok/sest. | 12804 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 11.1 GB | 128k | 32tok/sest. | 2712 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.8 GB | – | 21tok/sest. | 2161 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 47.0 GB | – | 22tok/sest. | 4838 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.3 GB | – | 11tok/sest. | 1926 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 39.1 GB | – | 31tok/sest. | 2460 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | offload | 48.9 GB | – | 5tok/sest. | 731 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 47.0 GB | – | 27tok/sest. | 5757 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 33.8 GB | – | 41tok/sest. | 8363 tok/s | chat, coding, agents, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 50.6 GB | – | 2tok/sest. | 278 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 93.9 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.7 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 75.3 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 78.9 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 61.2 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