AMD Radeon RX 7900 XTX
24 GB · 960 GB/s · 355 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 @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q5_K_M | fits | 21.5 GB | 56k98k with q8 cache | 24tok/sest. | 694 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q5_K_M | fits | 21.3 GB | 59k104k with q8 cache | 24tok/sest. | 694 tok/s | chat, coding |
| Gemma 4 31B | Q4_K_M | fits | 21.3 GB | 54k103k with q8 cache | 24tok/sest. | 619 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | fits | 22.3 GB | 68k106k with q8 cache | 123tok/sest. | 4957 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q5_K_M | fits | 21.4 GB | 58k102k with q8 cache | 24tok/sest. | 694 tok/s | chat, coding |
| Gemma 4 26B-A4B | UD-Q5_K_M | fits | 21.5 GB | 98k160k with q8 cache | 76tok/sest. | 4410 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | fits | 22.2 GB | 72k113k with q8 cache | 123tok/sest. | 4957 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q5_K_M | fits | 22.6 GB | 42k73k with q8 cache | 60tok/sest. | 2588 tok/s | chat, coding, agents |
| Devstral Small 2 24B Mistral AI | Q5_K_M | fits | 21.6 GB | 41k76k with q8 cache | 24tok/sest. | 733 tok/s | chat, coding |
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.0 GB | 128k | 98tok/sest. | 3701 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | fits | 21.3 GB | 51k91k with q8 cache | 63tok/sest. | 2280 tok/s | chat, coding, agents |
| Gemma 4 12B | Q8_0 | fits | 13.6 GB | 256k | 39tok/sest. | 1610 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.9 GB | 256k | 50tok/sest. | 2007 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q5_K_M | fits | 21.6 GB | 41k76k with q8 cache | 24tok/sest. | 733 tok/s | chat, coding |
| Gemma 3 27B | Q5_K_M | fits | 21.8 GB | 48k89k with q8 cache | 24tok/sest. | 737 tok/s | chat, coding |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 19.4 GB | 55k101k with q8 cache | 27tok/sest. | 1115 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 20.6 GB | 40k | 25tok/sest. | 1002 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.6 GB | 97k128k with q8 cache | 39tok/sest. | 1653 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.6 GB | 40k | 39tok/sest. | 1653 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 21.7 GB | 16k | 24tok/sest. | 1007 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.2 GB | 256k | 94tok/sest. | 3754 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.6 GB | 100k183k with q8 cache | 39tok/sest. | 1597 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 14.7 GB | 84k128k with q8 cache | 36tok/sest. | 1520 tok/s | chat, coding, agents |
| Gemma 4 E4B | Q8_0 | fits | 9.5 GB | 128k | 58tok/sest. | 2521 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.9 GB | 125k | 118tok/sest. | 8245 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 11.1 GB | 124k128k with q8 cache | 49tok/sest. | 1746 tok/s | chat, coding, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.8 GB | – | 15tok/sest. | 1196 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 47.0 GB | – | 18tok/sest. | 2706 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 39.1 GB | – | 22tok/sest. | 1356 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 48.9 GB | – | 4tok/sest. | 410 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 47.0 GB | – | 21tok/sest. | 3220 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 33.8 GB | – | 23tok/sest. | 4559 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.3 GB | – | 51tok/sest. | 3722 tok/s | chat, coding, long documents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 27.4 GB | 15k28k with q8 cache | 8tok/sest. | 390 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 27.5 GB | 15k28k with q8 cache | 8tok/sest. | 447 tok/s | chat |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 93.9 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.7 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 75.3 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 78.9 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.3 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 61.2 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 50.6 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