AMD Radeon RX 7900 XT
20 GB · 800 GB/s · 315 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 @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Gemma 4 26B-A4B | UD-Q4_K_M | fits | 18.4 GB | 95k154k with q8 cache | 63tok/sest. | 3247 tok/s | chat, coding, agents, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.0 GB | 128k | 65tok/sest. | 2427 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 14.3 GB | 256k | 31tok/sest. | 1248 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.1 GB | 255k256k with q8 cache | 38tok/sest. | 1528 tok/s | chat, coding, long documents |
| Ministral 3 14B Mistral AI | Q4_K_M | fits | 18.8 GB | 66k120k with q8 cache | 23tok/sest. | 730 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.3 GB | 70k127k with q8 cache | 24tok/sest. | 1010 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.3 GB | 40k | 24tok/sest. | 1010 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.4 GB | 256k | 66tok/sest. | 2648 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.1 GB | 72k130k with q8 cache | 24tok/sest. | 999 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q6_K | fits | 18.2 GB | 70k128k with q8 cache | 24tok/sest. | 923 tok/s | chat, coding, agents |
| Gemma 4 E4B | Q8_0 | fits | 10.6 GB | 128k | 44tok/sest. | 2001 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.6 GB | 125k | 62tok/sest. | 4270 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.3 GB | 93k128k with q8 cache | 29tok/sest. | 1085 tok/s | chat, coding |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 20.6 GB | 42k74k with q8 cache | 14tok/sest. | 503 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 41.8 GB | – | 10tok/sest. | 730 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 21.0 GB | 37k66k with q8 cache | 13tok/sest. | 498 tok/s | chat, coding |
| Gemma 4 31B | Q4_K_M | offload | 24.0 GB | 6k19k with q8 cache | 7tok/sest. | 420 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 40.0 GB | – | 14tok/sest. | 731 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | offload | 23.1 GB | – | 36tok/sest. | 2833 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 20.9 GB | 39k68k with q8 cache | 13tok/sest. | 499 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 23.0 GB | – | 36tok/sest. | 2841 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 21.5 GB | 23k40k with q8 cache | 22tok/sest. | 1465 tok/s | chat, coding, agents |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 24.5 GB | 31k56k with q8 cache | 7tok/sest. | 448 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.2 GB | – | 16tok/sest. | 2844 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.7 GB | – | 30tok/sest. | 1984 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 24.5 GB | 11k20k with q8 cache | 12tok/sest. | 981 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 35.6 GB | – | 3tok/sest. | 192 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 22.0 GB | 30k58k with q8 cache | 10tok/sest. | 543 tok/s | chat, coding |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 24.5 GB | 31k56k with q8 cache | 7tok/sest. | 448 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 35.7 GB | – | 3tok/sest. | 237 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 19.6 GB | 40k | 20tok/sest. | 632 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q4_K_M | offload | 22.0 GB | 16k | 10tok/sest. | 591 tok/s | chat, coding |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 96.7 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.2 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.2 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 86.8 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.7 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 47.9 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 62.5 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 54.9 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 47.9 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 60.8 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