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 @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Gemma 4 26B-A4B | UD-Q4_K_M | fits | 20.0 GB | 252k256k with q8 cache | 57tok/sest. | 3122 tok/s | chat, coding, agents, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 15.8 GB | 128k | 56tok/sest. | 2022 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 15.7 GB | 256k | 35tok/sest. | 1297 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 14.5 GB | 256k | 38tok/sest. | 1543 tok/s | chat, coding, long documents |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 9.8 GB | 256k | 60tok/sest. | 2404 tok/s | chat, coding, long documents |
| Gemma 4 E4B | Q8_0 | fits | 12.7 GB | 128k | 44tok/sest. | 2164 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 15.9 GB | 125k | 42tok/sest. | 2892 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q5_K_M | fits | 22.9 GB | 128k | 23tok/sest. | 854 tok/s | chat, coding, long documents |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 25.0 GB | 101k177k with q8 cache | 12tok/sest. | 505 tok/s | chat, coding |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 43.7 GB | – | 9tok/sest. | 666 tok/s | chat |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 25.4 GB | 96k168k with q8 cache | 12tok/sest. | 501 tok/s | chat, coding |
| Gemma 4 31B | Q4_K_M | offload | 29.4 GB | 54k103k with q8 cache | 6tok/sest. | 435 tok/s | chat, coding |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 41.8 GB | – | 12tok/sest. | 590 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q4_K_M | offload | 24.7 GB | 68k106k with q8 cache | 44tok/sest. | 2471 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 25.3 GB | 97k170k with q8 cache | 12tok/sest. | 501 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 24.6 GB | 72k113k with q8 cache | 45tok/sest. | 2478 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 25.2 GB | 92k160k with q8 cache | 18tok/sest. | 1151 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 34.9 GB | 55k101k with q8 cache | 4tok/sest. | 374 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.9 GB | – | 19tok/sest. | 2730 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 30.6 GB | – | 33tok/sest. | 1636 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 30.8 GB | 51k91k with q8 cache | 7tok/sest. | 631 tok/s | chat, coding, agents |
| Gemma 3 27B | Q4_K_M | offload | 27.4 GB | 78k128k with q8 cache | 8tok/sest. | 585 tok/s | chat, coding |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 34.9 GB | 55k101k with q8 cache | 4tok/sest. | 374 tok/s | chat, coding |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 29.2 GB | 90k165k with q8 cache | 6tok/sest. | 528 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 29.9 GB | 40k | 6tok/sest. | 444 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q4_K_M | offload | 24.2 GB | 120k128k with q8 cache | 16tok/sest. | 761 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q4_K_M | offload | 24.2 GB | 40k | 16tok/sest. | 761 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q4_K_M | offload | 34.8 GB | 16k | 4tok/sest. | 410 tok/s | chat, coding |
| Ministral 3 8B Mistral AI | Q4_K_M | offload | 23.4 GB | 126k229k with q8 cache | 21tok/sest. | 788 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q4_K_M | offload | 26.7 GB | 106k128k with q8 cache | 9tok/sest. | 652 tok/s | chat, coding, agents |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 102.5 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 104.3 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 78.1 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 102.7 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 53.6 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 49.8 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 65.1 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 66.8 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 49.8 GB | – | – | – | – |
| Qwen3 32B Alibaba Qwen | Q4_K_M | won't run | 52.0 GB | 15k28k with q8 cache | – | – | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | won't run | 52.0 GB | 15k28k with q8 cache | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 81.2 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