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 @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.5 GB | 46k82k with q8 cache | 12tok/sest. | 1169 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.1 GB | 53k92k with q8 cache | 12tok/sest. | 1169 tok/s | – |
| Gemma 4 31B | Q6_K | fits | 25.7 GB | 73k137k with q8 cache | 13tok/sest. | 1020 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q6_K | fits | 28.4 GB | 119k187k with q8 cache | 79tok/sest. | 10021 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.1 GB | 53k92k with q8 cache | 12tok/sest. | 1169 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.2 GB | 204k256k with q8 cache | 47tok/sest. | 7636 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 27.9 GB | 136k213k with q8 cache | 80tok/sest. | 10021 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 30.9 GB | 12k22k with q8 cache | 37tok/sest. | 5608 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.4 GB | 43k79k with q8 cache | 13tok/sest. | 1318 tok/s | – |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 28.9 GB | 174k237k with q8 cache | 109tok/sest. | 9524 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.3 GB | 128k | 80tok/sest. | 7253 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q6_K | fits | 25.0 GB | 70k126k with q8 cache | 65tok/sest. | 7250 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q6_K | fits | 27.9 GB | 20k38k with q8 cache | 12tok/sest. | 902 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.1 GB | 256k | 27tok/sest. | 2660 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.0 GB | 256k | 36tok/sest. | 3369 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.4 GB | 43k79k with q8 cache | 13tok/sest. | 1318 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q6_K | fits | 27.9 GB | 20k38k with q8 cache | 12tok/sest. | 943 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 28.6 GB | 38k72k with q8 cache | 12tok/sest. | 1185 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.5 GB | 105k191k with q8 cache | 22tok/sest. | 2187 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 16.7 GB | 40k | 21tok/sest. | 2032 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.1 GB | 128k | 36tok/sest. | 3556 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.1 GB | 40k | 36tok/sest. | 3556 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 16.9 GB | 16k | 20tok/sest. | 2046 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.3 GB | 256k | 73tok/sest. | 6782 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.3 GB | 158k256k with q8 cache | 35tok/sest. | 3323 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 10.8 GB | 128k | 33tok/sest. | 3298 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 8.7 GB | 128k | 42tok/sest. | 4083 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.6 GB | 125k | 144tok/sest. | 23830 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 8.0 GB | 128k | 46tok/sest. | 3672 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.1 GB | – | 25tok/sest. | 2671 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 46.3 GB | – | 28tok/sest. | 6256 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.0 GB | – | 12tok/sest. | 2060 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 38.5 GB | – | 40tok/sest. | 3574 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | offload | 44.5 GB | – | 9tok/sest. | 1261 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 46.3 GB | – | 36tok/sest. | 7867 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 33.5 GB | – | 44tok/sest. | 9993 tok/s | chat, coding, agents, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 42.9 GB | – | 3tok/sest. | 367 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 91.7 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.3 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 74.6 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 72.9 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 60.2 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