readygpu

NVIDIA GeForce RTX 4080 Super vs AMD Radeon RX 7900 XT

For running models locally, priced in India. At 8k context the first runs 16 models fully in memory, the second 23.

In short

The AMD Radeon RX 7900 XT has more memory for models: 20 GB against 16 GB. At 8k context the AMD Radeon RX 7900 XT runs 23 of the models we track fully in memory and the NVIDIA GeForce RTX 4080 Super 16; only the AMD Radeon RX 7900 XT holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 4080 Super and the AMD Radeon RX 7900 XT are about as fast as each other (estimated).

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

NVIDIA GeForce RTX 4080 Super

Not priced here

Add to build
AMD Radeon RX 7900 XT

Not priced here

Add to build

Specifications

SpecNVIDIA GeForce RTX 4080 SuperAMD Radeon RX 7900 XT
GPUGeForce RTX 4080 SuperRadeon RX 7900 XT
Memory16 GB GDDR6X20 GB GDDR6
Memory bus256-bit320-bit
Memory bandwidth736 GB/s800 GB/s
FP16 compute104 TFLOPS103 TFLOPS
SoftwareCUDAROCm
Board power320 W315 W
PCIe generationGen 4Gen 4
PCIe lanesx16x16

What each runs

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

ModelNVIDIA GeForce RTX 4080 SuperAMD Radeon RX 7900 XT
Qwen 3.8 27Boffload26tok/sUD-Q4_K_M
Qwen 3.6 27Boffload25tok/sQ4_K_M
Qwen 3.5 27Boffload25tok/sQ4_K_M
Gemma 4 26B-A4Boffload88tok/sUD-Q4_K_M
Devstral Small 2 24B29tok/sQ4_K_M24tok/sQ5_K_M
GLM 4.7 Flashoffload76tok/sQ4_K_M
gpt-oss 20B104tok/sMXFP4100tok/sMXFP4
Qwen3 Coder 30B-A3Boffload100tok/sQ4_K_M
Gemma 4 12B35tok/sQ8_034tok/sQ8_0
Qwen 3.5 9B46tok/sQ8_045tok/sQ8_0
Mistral Small 3.2 24B29tok/sQ4_K_M24tok/sQ5_K_M
Gemma 3 27Boffload25tok/sQ4_K_M
Qwen3 14B34tok/sQ6_K26tok/sQ8_0
Ministral 3 14B29tok/sQ8_028tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B46tok/sQ8_044tok/sQ8_0
Qwen3 8B46tok/sQ8_044tok/sQ8_0
Phi-4 14B33tok/sQ6_K26tok/sQ8_0
Qwen 3.5 4B95tok/sQ8_092tok/sQ8_0
Ministral 3 8B45tok/sQ8_043tok/sQ8_0
Granite 4.2 8B43tok/sQ8_041tok/sQ8_0
Gemma 4 E4B54tok/sQ8_052tok/sQ8_0
LFM2.5 8B-A1B187tok/sQ8_0180tok/sQ8_0
Llama 3.1 8B60tok/sQ6_K57tok/sQ6_K
Qwen 3.5 122B-A10Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadoffload
Qwen 3.6 35B-A3Boffloadoffload
GLM 4.5 Airwon't runoffload
Qwen 3.5 35B-A3Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 32Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Llama 3.3 70Bwon't runoffload
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
Qwen3 Coder Nextwon't runwon't run
gpt-oss 120Bwon't runwon't run
Qwen3 Next 80B-A3Bwon't runwon't run

Questions

Which is better for local AI, the NVIDIA GeForce RTX 4080 Super or the AMD Radeon RX 7900 XT?
Choose the AMD Radeon RX 7900 XT to run bigger models.
Which can run bigger models, the NVIDIA GeForce RTX 4080 Super or the AMD Radeon RX 7900 XT?
At 8k context the AMD Radeon RX 7900 XT runs 23 of the models we track fully in memory and the NVIDIA GeForce RTX 4080 Super 16; only the AMD Radeon RX 7900 XT holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 4080 Super or the AMD Radeon RX 7900 XT?
On the models both run fully in memory, the NVIDIA GeForce RTX 4080 Super and the AMD Radeon RX 7900 XT are about as fast as each other (estimated).

More comparisons