AMD Radeon RX 7900 XTX
24 GB · 960 GB/s · 355 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 @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 37.2 GB | 256k | 14tok/sest. | 529 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 44.2 GB | 204k256k with q8 cache | 47tok/sest. | 941 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 14tok/sest. | 529 tok/s | chat |
| Gemma 4 31B | Q8_0 | fits | 43.2 GB | 165k256k with q8 cache | 12tok/sest. | 502 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 42.3 GB | 275k436k with q8 cache | 59tok/sest. | 816 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 39.0 GB | 256k | 54tok/sest. | 2572 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 14tok/sest. | 529 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.8 GB | 256k | 45tok/sest. | 3122 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 39.0 GB | 256k | 54tok/sest. | 2572 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 38.3 GB | 198k | 26tok/sest. | 1213 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 45.4 GB | 134k244k with q8 cache | 11tok/sest. | 473 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 35.4 GB | 256k | 76tok/sest. | 3460 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 40.8 GB | 544k742k with q8 cache | 89tok/sest. | 1930 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 16.3 GB | 128k | 56tok/sest. | 2022 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 44.3 GB | 149k256k with q8 cache | 20tok/sest. | 748 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 16.2 GB | 256k | 35tok/sest. | 1297 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 15.0 GB | 256k | 38tok/sest. | 1543 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 39.2 GB | 128k | 13tok/sest. | 648 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 45.4 GB | 128k | 11tok/sest. | 473 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 35.4 GB | 195k256k with q8 cache | 15tok/sest. | 608 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 36.7 GB | 40k | 14tok/sest. | 517 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 28.2 GB | 128k | 19tok/sest. | 782 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 28.2 GB | 40k | 19tok/sest. | 782 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 41.6 GB | 16k | 12tok/sest. | 519 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 60tok/sest. | 2404 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 27.5 GB | 256k | 19tok/sest. | 792 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 30.8 GB | 128k | 17tok/sest. | 711 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 13.2 GB | 128k | 44tok/sest. | 2164 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 16.4 GB | 125k | 42tok/sest. | 2892 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 24.2 GB | 128k | 22tok/sest. | 854 tok/s | chat, coding, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 50.3 GB | – | 33tok/sest. | 1985 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 54.1 GB | – | 21tok/sest. | 1204 tok/s | chat, coding, long documents |
| gpt-oss 120B OpenAI | MXFP4 | offload | 65.6 GB | – | 11tok/sest. | 1142 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 67.3 GB | 15k28k with q8 cache | 3tok/sest. | 191 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 50.3 GB | – | 36tok/sest. | 2169 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 52.5 GB | 40k | 5tok/sest. | 197 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 52.5 GB | 104k128k with q8 cache | 5tok/sest. | 264 tok/s | chat |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 103.0 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 104.8 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 78.6 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 103.2 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 81.7 GB | 17k31k with q8 cache | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- Radeon RX 7900 XTX
- Memory
- 24 GB GDDR6
- Memory bus
- 384-bit
- Memory bandwidth
- 960 GB/s
- FP16 compute
- 123 TFLOPS
- Software
- ROCm
- Board power
- 355 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16