readygpu

AMD Radeon RX 7900 XT vs AMD Radeon RX 7900 XTX

For running models locally, priced in Canada. At 32k context the first runs 18 models fully in memory, the second 26.

In short

The AMD Radeon RX 7900 XTX has more memory for models: 24 GB against 20 GB. At 32k context the AMD Radeon RX 7900 XTX runs 26 of the models we track fully in memory and the AMD Radeon RX 7900 XT 18; only the AMD Radeon RX 7900 XTX holds Gemma 4 31B. On the models both run fully in memory, the AMD Radeon RX 7900 XTX is about 1.2× as fast as the AMD Radeon RX 7900 XT (estimated, median across models).

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

AMD Radeon RX 7900 XT

$2,175

Amazon

Add to build
AMD Radeon RX 7900 XTX

Not priced here

Add to build

Specifications

SpecAMD Radeon RX 7900 XTAMD Radeon RX 7900 XTX
GPURadeon RX 7900 XTRadeon RX 7900 XTX
Memory20 GB GDDR624 GB GDDR6
Memory bus320-bit384-bit
Memory bandwidth800 GB/s960 GB/s
FP16 compute103 TFLOPS123 TFLOPS
SoftwareROCmROCm
Board power315 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 7900 XTAMD Radeon RX 7900 XTX
Qwen 3.8 27B24tok/sUD-Q4_K_M24tok/sUD-Q5_K_M
Qwen 3.6 27B23tok/sQ4_K_M24tok/sQ5_K_M
Gemma 4 31Boffload24tok/sQ4_K_M
Qwen 3.5 27B23tok/sQ4_K_M24tok/sQ5_K_M
Qwen 3.6 35B-A3Boffload123tok/sUD-Q4_K_M
Gemma 4 26B-A4B75tok/sUD-Q4_K_M76tok/sUD-Q5_K_M
Qwen 3.5 35B-A3Boffload123tok/sQ4_K_M
GLM 4.7 Flashoffload60tok/sQ5_K_M
Devstral Small 2 24Boffload24tok/sQ5_K_M
gpt-oss 20B82tok/sMXFP498tok/sMXFP4
Qwen3 Coder 30B-A3Boffload63tok/sQ4_K_M
Gemma 4 12B33tok/sQ8_039tok/sQ8_0
Qwen 3.5 9B41tok/sQ8_050tok/sQ8_0
Gemma 3 27Boffload24tok/sQ5_K_M
Mistral Small 3.2 24Boffload24tok/sQ5_K_M
Ministral 3 14B27tok/sQ6_K27tok/sQ8_0
Qwen3 14B25tok/sQ6_K25tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B33tok/sQ8_039tok/sQ8_0
Qwen3 8B33tok/sQ8_039tok/sQ8_0
Phi-4 14B24tok/sQ6_K24tok/sQ8_0
Qwen 3.5 4B79tok/sQ8_094tok/sQ8_0
Ministral 3 8B32tok/sQ8_039tok/sQ8_0
Granite 4.2 8B30tok/sQ8_036tok/sQ8_0
Gemma 4 E4B48tok/sQ8_058tok/sQ8_0
LFM2.5 8B-A1B99tok/sQ8_0118tok/sQ8_0
Llama 3.1 8B40tok/sQ6_K49tok/sQ6_K
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
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 32Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
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

Questions

Which is better for local AI, the AMD Radeon RX 7900 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.
Which can run bigger models, the AMD Radeon RX 7900 XT or the AMD Radeon RX 7900 XTX?
At 32k context the AMD Radeon RX 7900 XTX runs 26 of the models we track fully in memory and the AMD Radeon RX 7900 XT 18; only the AMD Radeon RX 7900 XTX holds Gemma 4 31B.
Which is faster for local AI, the AMD Radeon RX 7900 XT or the AMD Radeon RX 7900 XTX?
On the models both run fully in memory, the AMD Radeon RX 7900 XTX is about 1.2× as fast as the AMD Radeon RX 7900 XT (estimated, median across models).

More comparisons