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.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| AmazonASRock AMD Radeon RX 7900 XT Phantom Gaming 20GB OC Graphics Card GDDR6 320… | New | $800 | In stock | 25 min ago | Buy |
| AmazonSapphire 21323-01-20G AMD Radeon RX 7900 XT Gaming Graphics Card with 20GB GDDR6 | New | $850 | In stock | 25 min ago | Buy |
| AmazonSapphire 11323-02-20G Pulse AMD Radeon RX 7900 XT Gaming Graphics Card with… | refurbished | $990 | In stock | 25 min ago | Buy |
| AmazonASRock AMD Radeon RX 7900 XT Phantom Gaming 20GB OC Graphics Card 320 Bit 7680… | refurbished | $1,000 | In stock | 25 min ago | Buy |
| AmazonPowerColor Hellhound AMD Radeon RX 7900 XT Graphics Card | refurbished | $1,050 | In stock | 25 min ago | Buy |
| AmazonSapphire Pulse AMD Radeon RX 7900 XT Triple Fan Graphics Card | New | $1,140 | In stock | 25 min ago | Buy |
| AmazonXFX Speedster MERC310 AMD Radeon RX 7900XT Black Gaming Graphics Card with… | New | $1,190 | In stock | 25 min ago | Buy |
| AmazonXFX Speedster MERC310 AMD Radeon RX 7900 XT Gaming Graphics Card with 20GB GDDR6 | New | $1,200 | In stock | 25 min ago | Buy |
| AmazonSapphire 11323-02-20G Pulse AMD Radeon RX 7900 XT Gaming Graphics Card with… | New | $1,220 | In stock | 25 min ago | Buy |
| AmazonASUS TUF Gaming AMD Radeon RX 7900 XT OC Edition Gaming Graphics Card | New | $1,220+ $14 delivery | In stock | 25 min ago | Buy |
| AmazonPowerColor AMD Radeon RX 7900 XT Graphics Card | New | $1,240 | In stock | 25 min ago | Buy |
Price history
Lowest price shown each day over the last 90 days.
Not enough price history yet.
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 | 144k253k with q8 cache | 13tok/sest. | 527 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 32.4 GB | 151k256k with q8 cache | 13tok/sest. | 527 tok/s | chat |
| Gemma 4 31B | Q8_0 | fits | 37.9 GB | 70k132k with q8 cache | 11tok/sest. | 481 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.4 GB | 105k164k with q8 cache | 59tok/sest. | 3171 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 32.4 GB | 151k256k with q8 cache | 13tok/sest. | 527 tok/s | chat |
| Gemma 4 26B-A4B | Q8_0 | fits | 28.1 GB | 256k | 46tok/sest. | 3247 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.4 GB | 105k164k with q8 cache | 59tok/sest. | 3171 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 34.6 GB | 129k198k with q8 cache | 30tok/sest. | 1573 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 35.0 GB | 84k154k with q8 cache | 12tok/sest. | 519 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.7 GB | 256k | 70tok/sest. | 3910 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q5_K_M | fits | 34.9 GB | 322k439k with q8 cache | 97tok/sest. | 2547 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.5 GB | 128k | 65tok/sest. | 2427 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 37.9 GB | 68k123k with q8 cache | 27tok/sest. | 1135 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | fits | 36.1 GB | 40k | 12tok/sest. | 269 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 14.8 GB | 256k | 31tok/sest. | 1248 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.6 GB | 256k | 38tok/sest. | 1528 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 33.8 GB | 118k128k with q8 cache | 13tok/sest. | 590 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 35.0 GB | 84k128k with q8 cache | 12tok/sest. | 519 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | fits | 36.2 GB | 72k128k with q8 cache | 12tok/sest. | 332 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 25.0 GB | 146k256k with q8 cache | 18tok/sest. | 730 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 26.3 GB | 40k | 17tok/sest. | 639 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.8 GB | 128k | 24tok/sest. | 1010 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.8 GB | 40k | 24tok/sest. | 1010 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.7 GB | 16k | 15tok/sest. | 642 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.9 GB | 256k | 66tok/sest. | 2648 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.6 GB | 206k256k with q8 cache | 24tok/sest. | 999 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.4 GB | 128k | 22tok/sest. | 923 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 11.1 GB | 128k | 44tok/sest. | 2001 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 13.1 GB | 125k | 62tok/sest. | 4270 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.8 GB | 128k | 29tok/sest. | 1085 tok/s | chat, coding, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 42.3 GB | – | 31tok/sest. | 1033 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 48.4 GB | – | 26tok/sest. | 2213 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 53.2 GB | – | 14tok/sest. | 1054 tok/s | chat |
| gpt-oss 120B OpenAI | MXFP4 | offload | 63.0 GB | – | 12tok/sest. | 1291 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 40.5 GB | – | 49tok/sest. | 1043 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | offload | 55.4 GB | – | 4tok/sest. | 270 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 48.4 GB | – | 30tok/sest. | 2525 tok/s | chat, coding, agents, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 61.3 GB | – | 2tok/sest. | 122 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 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