AMD Radeon RX 7900 XTX
24 GB · 960 GB/s · 355 W
Prices
Every retailer we track in Canada, 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 | Q8_0 | fits | 32.9 GB | 256k | 16tok/sest. | 629 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 42.3 GB | 204k256k with q8 cache | 62tok/sest. | 1309 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 32.4 GB | 256k | 16tok/sest. | 629 tok/s | chat |
| Gemma 4 31B | Q8_0 | fits | 37.9 GB | 165k256k with q8 cache | 14tok/sest. | 574 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 40.5 GB | 275k436k with q8 cache | 82tok/sest. | 1287 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.4 GB | 256k | 71tok/sest. | 3787 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 32.4 GB | 256k | 16tok/sest. | 629 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 28.1 GB | 256k | 55tok/sest. | 3877 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.4 GB | 256k | 71tok/sest. | 3787 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 34.6 GB | 198k | 36tok/sest. | 1879 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 35.0 GB | 134k244k with q8 cache | 15tok/sest. | 619 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.7 GB | 256k | 84tok/sest. | 4669 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 39.9 GB | 544k742k with q8 cache | 104tok/sest. | 3042 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.5 GB | 128k | 78tok/sest. | 2898 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 37.9 GB | 149k256k with q8 cache | 33tok/sest. | 1355 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q6_K | fits | 42.7 GB | 40k | 12tok/sest. | 321 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 14.8 GB | 256k | 38tok/sest. | 1490 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.6 GB | 256k | 45tok/sest. | 1824 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 33.8 GB | 128k | 15tok/sest. | 705 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 35.0 GB | 128k | 15tok/sest. | 619 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q6_K | fits | 42.7 GB | 78k128k with q8 cache | 12tok/sest. | 397 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 25.0 GB | 195k256k with q8 cache | 21tok/sest. | 872 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 26.3 GB | 40k | 20tok/sest. | 764 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.8 GB | 128k | 29tok/sest. | 1206 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.8 GB | 40k | 29tok/sest. | 1206 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.7 GB | 16k | 18tok/sest. | 767 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.9 GB | 256k | 79tok/sest. | 3162 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.6 GB | 256k | 29tok/sest. | 1193 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.4 GB | 128k | 26tok/sest. | 1102 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 11.1 GB | 128k | 52tok/sest. | 2389 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 13.1 GB | 125k | 74tok/sest. | 5099 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.8 GB | 128k | 35tok/sest. | 1295 tok/s | chat, coding, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 48.4 GB | – | 57tok/sest. | 2954 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 53.2 GB | – | 24tok/sest. | 1401 tok/s | chat, coding, long documents |
| gpt-oss 120B OpenAI | MXFP4 | offload | 63.0 GB | – | 17tok/sest. | 1701 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 55.4 GB | 15k28k with q8 cache | 7tok/sest. | 358 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 48.4 GB | – | 66tok/sest. | 3370 tok/s | chat, coding, agents, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 61.3 GB | 17k31k with q8 cache | 3tok/sest. | 161 tok/s | – |
| 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 | – | – | – | – |
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