AMD Radeon RX 7900 XT
20 GB · 800 GB/s · 315 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 @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 37.2 GB | 144k253k with q8 cache | 12tok/sest. | 443 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 151k256k with q8 cache | 12tok/sest. | 443 tok/s | chat |
| Gemma 4 31B | Q6_K | fits | 36.3 GB | 152k256k with q8 cache | 12tok/sest. | 421 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q6_K | fits | 31.9 GB | 256k | 51tok/sest. | 2154 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 151k256k with q8 cache | 12tok/sest. | 443 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.8 GB | 256k | 37tok/sest. | 2615 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 31.5 GB | 256k | 51tok/sest. | 2154 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 38.3 GB | 129k198k with q8 cache | 21tok/sest. | 1016 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q5_K_M | fits | 37.7 GB | 132k241k with q8 cache | 12tok/sest. | 396 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 35.4 GB | 256k | 63tok/sest. | 2897 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q5_K_M | fits | 35.8 GB | 322k439k with q8 cache | 81tok/sest. | 1616 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 16.3 GB | 128k | 47tok/sest. | 1693 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q6_K | fits | 37.4 GB | 137k246k with q8 cache | 17tok/sest. | 627 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 16.2 GB | 256k | 29tok/sest. | 1087 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 15.0 GB | 256k | 32tok/sest. | 1292 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q6_K | fits | 33.1 GB | 128k | 13tok/sest. | 542 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q5_K_M | fits | 37.7 GB | 128k | 12tok/sest. | 396 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 35.4 GB | 146k256k with q8 cache | 12tok/sest. | 509 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 36.7 GB | 40k | 12tok/sest. | 433 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 28.2 GB | 128k | 16tok/sest. | 655 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 28.2 GB | 40k | 16tok/sest. | 655 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q6_K | fits | 38.3 GB | 16k | 11tok/sest. | 434 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 50tok/sest. | 2013 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 27.5 GB | 206k256k with q8 cache | 16tok/sest. | 663 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 30.8 GB | 128k | 14tok/sest. | 596 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 13.2 GB | 128k | 37tok/sest. | 1812 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 16.4 GB | 125k | 35tok/sest. | 2422 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 24.2 GB | 128k | 19tok/sest. | 715 tok/s | chat, coding, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 44.2 GB | – | 20tok/sest. | 723 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 50.3 GB | – | 17tok/sest. | 1488 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 54.1 GB | – | 13tok/sest. | 906 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 42.3 GB | – | 29tok/sest. | 643 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 50.3 GB | – | 19tok/sest. | 1627 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 52.5 GB | 40k | 3tok/sest. | 148 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 52.5 GB | 72k128k with q8 cache | 3tok/sest. | 198 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 | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 65.6 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 67.3 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 81.7 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- Radeon RX 7900 XT
- Memory
- 20 GB GDDR6
- Memory bus
- 320-bit
- Memory bandwidth
- 800 GB/s
- FP16 compute
- 103 TFLOPS
- Software
- ROCm
- Board power
- 315 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16