AMD Radeon RX 9070 XT
16 GB · 640 GB/s · 304 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 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 @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q6_K | fits | 26.3 GB | 124k217k with q8 cache | 13tok/sest. | 997 tok/s | chat |
| Qwen 3.6 27B Alibaba Qwen | Q6_K | fits | 26.8 GB | 116k204k with q8 cache | 13tok/sest. | 997 tok/s | chat |
| Gemma 4 31B | Q5_K_M | fits | 27.6 GB | 97k179k with q8 cache | 13tok/sest. | 911 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q6_K | fits | 30.3 GB | 68k107k with q8 cache | 55tok/sest. | 6003 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q6_K | fits | 26.7 GB | 117k206k with q8 cache | 13tok/sest. | 997 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 28.1 GB | 153k245k with q8 cache | 37tok/sest. | 6147 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 29.9 GB | 85k133k with q8 cache | 55tok/sest. | 6003 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q6_K | fits | 28.0 GB | 106k183k with q8 cache | 28tok/sest. | 2978 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q6_K | fits | 29.7 GB | 68k124k with q8 cache | 12tok/sest. | 982 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 30.2 GB | 78k107k with q8 cache | 88tok/sest. | 4822 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.5 GB | 128k | 52tok/sest. | 4595 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q5_K_M | fits | 27.9 GB | 89k159k with q8 cache | 25tok/sest. | 2148 tok/s | chat, coding, agents |
| Gemma 4 12B | Q8_0 | fits | 14.8 GB | 256k | 25tok/sest. | 2363 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.6 GB | 256k | 30tok/sest. | 2892 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q6_K | fits | 27.7 GB | 95k128k with q8 cache | 13tok/sest. | 1117 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q6_K | fits | 29.7 GB | 68k124k with q8 cache | 12tok/sest. | 982 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 25.0 GB | 97k176k with q8 cache | 14tok/sest. | 1383 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 26.3 GB | 40k | 13tok/sest. | 1211 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.8 GB | 128k | 19tok/sest. | 1911 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.8 GB | 40k | 19tok/sest. | 1911 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.7 GB | 16k | 12tok/sest. | 1215 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.9 GB | 256k | 53tok/sest. | 5013 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.6 GB | 149k256k with q8 cache | 19tok/sest. | 1891 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.4 GB | 125k128k with q8 cache | 18tok/sest. | 1747 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 11.1 GB | 128k | 35tok/sest. | 3788 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 13.1 GB | 125k | 49tok/sest. | 8084 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.8 GB | 128k | 23tok/sest. | 2053 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 42.3 GB | – | 16tok/sest. | 1711 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 48.4 GB | – | 17tok/sest. | 3696 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 53.2 GB | – | 10tok/sest. | 1771 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 40.5 GB | – | 22tok/sest. | 1722 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 55.4 GB | – | 3tok/sest. | 455 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 48.4 GB | – | 19tok/sest. | 4217 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.7 GB | – | 33tok/sest. | 6824 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 36.1 GB | 40k | 5tok/sest. | 458 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 36.2 GB | 41k76k with q8 cache | 5tok/sest. | 566 tok/s | chat |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 97.2 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.7 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.7 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 87.3 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 63.0 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 61.3 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- Radeon RX 9070 XT
- Memory
- 16 GB GDDR6
- Memory bus
- 256-bit
- Memory bandwidth
- 640 GB/s
- FP16 compute
- 195 TFLOPS
- Software
- ROCm
- Board power
- 304 W
- PCIe generation
- Gen 5
- PCIe lanes
- x16