readygpu

AMD Radeon RX 7800 XT vs AMD Radeon RX 7900 XTX

For running models locally, priced in Germany. At 32k context the first runs 32 models fully in memory, the second 53.

In short

The AMD Radeon RX 7900 XTX has more memory for models: 24 GB against 16 GB. At 32k context the AMD Radeon RX 7900 XTX runs 53 of the models we track fully in memory and the AMD Radeon RX 7800 XT 32; only the AMD Radeon RX 7900 XTX holds Qwen 3.8 27B. On the models both run fully in memory, the AMD Radeon RX 7900 XTX is about 1.5× as fast as the AMD Radeon RX 7800 XT (estimated, median across models). In Germany the AMD Radeon RX 7800 XT costs 997 € at Amazon and the AMD Radeon RX 7900 XTX 1.555 € at eBay: the AMD Radeon RX 7800 XT is 558 € cheaper.

Updated . Speeds are estimates; how they are worked out.

AMD Radeon RX 7800 XT

997 €

Amazon

Add to build
AMD Radeon RX 7900 XTX

1.555 €

eBay

Add to build

Specifications

SpecAMD Radeon RX 7800 XTAMD Radeon RX 7900 XTX
GPURadeon RX 7800 XTRadeon RX 7900 XTX
Memory16 GB GDDR624 GB GDDR6
Memory bus256-bit384-bit
Memory bandwidth624 GB/s960 GB/s
FP16 compute74 TFLOPS123 TFLOPS
SoftwareROCmROCm
Board power263 W355 W
PCIe generationGen 4Gen 4
PCIe lanesx16x16

What each runs

Estimated decode speed with the most precise quant that fits each one est.

ModelAMD Radeon RX 7800 XTAMD Radeon RX 7900 XTX
Qwen 3.8 27Boffload23tok/sQ5_K_M
Qwen 3.6 27Boffload24tok/sQ5_K_M
Gemma 4 31Boffload24tok/sQ4_K_M
Qwen 3.6 35B-A3Boffload122tok/sQ4_K_M
Qwen 3.5 27Boffload24tok/sQ5_K_M
Gemma 4 26B-A4Boffload72tok/sQ6_K
Qwen 3.5 35B-A3Boffload123tok/sQ4_K_M
GLM 4.7 Flashoffload60tok/sQ5_K_M
Devstral Small 2 24Boffload24tok/sQ5_K_M
Nemotron 3.5 Lightning 30B-A3Boffload129tok/sMXFP4
gpt-oss 20B64tok/sMXFP498tok/sMXFP4
Qwen3 Coder 30B-A3Boffload63tok/sQ4_K_M
Gemma 4 12B25tok/sQ8_039tok/sQ8_0
Qwen 3.5 9B32tok/sQ8_050tok/sQ8_0
Gemma 3 27Boffload24tok/sQ5_K_M
Mistral Small 3.2 24Boffload24tok/sQ5_K_M
Qwen3 14B24tok/sQ4_K_M25tok/sQ8_0
Ministral 3 14B23tok/sQ5_K_M27tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B25tok/sQ8_039tok/sQ8_0
Qwen3 8B25tok/sQ8_039tok/sQ8_0
Phi-4 14Boffload24tok/sQ8_0
Qwen 3.5 4B61tok/sQ8_094tok/sQ8_0
Ministral 3 8B25tok/sQ8_039tok/sQ8_0
Granite 4.2 8B23tok/sQ8_036tok/sQ8_0
Gemma 4 E4B37tok/sQ8_058tok/sQ8_0
LFM2.5 8B-A1B77tok/sQ8_0118tok/sQ8_0
Llama 3.1 8B32tok/sQ6_K49tok/sQ6_K
Qwen2.5 0.5B368tok/sQ8_0566tok/sQ8_0
Qwen3.5 0.8B278tok/sQ8_0428tok/sQ8_0
Qwen3.5 2B185tok/sQ5_K_M284tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B121tok/sQ8_0186tok/sQ8_0
MiniCPM5 2B84tok/sQ8_0129tok/sQ8_0
Spark X2.5 4B80tok/smlx-4bit123tok/smlx-4bit
LFM2.5 2.6B70tok/sQ8_0108tok/sQ8_0
LFM2.5 VL 3B70tok/sQ8_0108tok/sQ8_0
Kimi VL A3B Thinking 250670tok/sQ4_K_M77tok/sQ8_0
Mellum2.1 12B A2.5B Thinking65tok/sQ8_0100tok/sQ8_0
Kimi VL A3B58tok/smlx-6bit74tok/smlx-8bit
granite vision 4.1 4b54tok/sQ8_084tok/sQ8_0
granite 4.2 3b52tok/sQ8_080tok/sQ8_0
GLM 4 9B 041436tok/smlx-5bit55tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B34tok/sQ8_053tok/sQ8_0
GLM 4.6V Flash30tok/sQ8_047tok/sQ8_0
DeepSeek R1 Distill Llama 8B27tok/sQ8_041tok/sQ8_0
GLM 4.1V 9B Thinking26tok/smlx-8bit40tok/smlx-8bit
Ministral 3 8B Reasoning 251225tok/sQ8_039tok/sQ8_0
LFM2.5 24B A2Boffload71tok/sQ6_K
DeepSeek R1 Distill Qwen 14Boffload24tok/sQ8_0
Devstral Small 2507offload24tok/sQ5_K_M
Magistral Small 2506offload24tok/sQ5_K_M
Magistral Small 2507offload24tok/sQ5_K_M
Magistral Small 2509offload24tok/sQ5_K_M
Qwen3.8 27B OBLITERATEDoffload23tok/smlx-4bit
Qwen 3.5 122B-A10Boffloadoffload
Qwen3 Coder Nextwon't runoffload
Mistral Small 4 119Boffloadoffload
GLM 4.5 Airwon't runoffload
Qwen3 Next 80B-A3Bwon't runoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 32Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
granite 4.2 30boffloadoffload
DeepSeek V4 Flashwon't runwon't run
GLM 5.3 Flashwon't runwon't run
Qwen 3.8 Flash Nextwon't runwon't run
MiniMax M2.7won't runwon't run
Nemotron 3 Super 120B-A12Bwon't runwon't run
gpt-oss 120Bwon't runwon't run
Llama 3.3 70Bwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Distill Llama 70Bwon't runwon't run
DeepSeek R1 Zerowon't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won't runwon't run
DeepSeek V3.1 Terminuswon't runwon't run
DeepSeek V3.2won't runwon't run
DeepSeek V4 Flash 0731won't runwon't run
DeepSeek V4 Flash Vision Expwon't runwon't run
Devstral 2 123B Instruct 2512won't runwon't run
GLM 4.5Vwon't runwon't run
GLM 4.6won't runwon't run
GLM 4.6Vwon't runwon't run
GLM 4.7won't runwon't run
GLM 5.1won't runwon't run
GLM 5.2won't runwon't run
GLM 5.3won't runwon't run
Kimi Dev 72Bwon't runwon't run
Kimi K2won't runwon't run
Kimi K2 Instruct 0905won't runwon't run
Kimi K2 Thinkingwon't runwon't run
Kimi K2.5won't runwon't run
MiniMax M2won't runwon't run
MiniMax M2.1won't runwon't run
MiniMax M2.5won't runwon't run
MiniMax M3won't runwon't run
Mistral Medium 3.5 128Bwon't runwon't run

Questions

Which is better for local AI, the AMD Radeon RX 7800 XT or the AMD Radeon RX 7900 XTX?
Choose the AMD Radeon RX 7900 XTX to run bigger models. Choose the AMD Radeon RX 7900 XTX for speed. Choose the AMD Radeon RX 7800 XT to spend less.
Which can run bigger models, the AMD Radeon RX 7800 XT or the AMD Radeon RX 7900 XTX?
At 32k context the AMD Radeon RX 7900 XTX runs 53 of the models we track fully in memory and the AMD Radeon RX 7800 XT 32; only the AMD Radeon RX 7900 XTX holds Qwen 3.8 27B.
Which is faster for local AI, the AMD Radeon RX 7800 XT or the AMD Radeon RX 7900 XTX?
On the models both run fully in memory, the AMD Radeon RX 7900 XTX is about 1.5× as fast as the AMD Radeon RX 7800 XT (estimated, median across models).
What is the price difference between the AMD Radeon RX 7800 XT and the AMD Radeon RX 7900 XTX?
In Germany the AMD Radeon RX 7800 XT costs 997 € at Amazon and the AMD Radeon RX 7900 XTX 1.555 € at eBay: the AMD Radeon RX 7800 XT is 558 € cheaper.

More comparisons