readygpu

NVIDIA GeForce RTX 5070 Ti vs AMD Radeon RX 7900 XTX

For running models locally, priced in Canada. At 32k context the first runs 30 models fully in memory, the second 48.

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 48 of the models we track fully in memory and the NVIDIA GeForce RTX 5070 Ti 30; only the AMD Radeon RX 7900 XTX holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 5070 Ti is about 1.1× as fast as the AMD Radeon RX 7900 XTX (estimated, median across models). In Canada the NVIDIA GeForce RTX 5070 Ti costs $1,650 at eBay and the AMD Radeon RX 7900 XTX $2,500 at eBay (used): the NVIDIA GeForce RTX 5070 Ti is $850 cheaper.

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

NVIDIA GeForce RTX 5070 Ti

$1,650

eBay

Add to build
AMD Radeon RX 7900 XTX

$2,500

eBay, used (asking)

Add to build

Specifications

SpecNVIDIA GeForce RTX 5070 TiAMD Radeon RX 7900 XTX
GPUGeForce RTX 5070 TiRadeon RX 7900 XTX
Memory16 GB GDDR724 GB GDDR6
Memory bus256-bit384-bit
Memory bandwidth896 GB/s960 GB/s
FP16 compute88 TFLOPS123 TFLOPS
SoftwareCUDAROCm
Board power300 W355 W
PCIe generationGen 5Gen 4
PCIe lanesx16x16

What each runs

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

ModelNVIDIA GeForce RTX 5070 TiAMD 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
gpt-oss 20B103tok/sMXFP498tok/sMXFP4
Qwen3 Coder 30B-A3Boffload63tok/sQ4_K_M
Gemma 4 12B41tok/sQ8_039tok/sQ8_0
Qwen 3.5 9B52tok/sQ8_050tok/sQ8_0
Gemma 3 27Boffload24tok/sQ5_K_M
Mistral Small 3.2 24Boffload24tok/sQ5_K_M
Qwen3 14B39tok/sQ4_K_M25tok/sQ8_0
Ministral 3 14B37tok/sQ5_K_M27tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B41tok/sQ8_039tok/sQ8_0
Qwen3 8B41tok/sQ8_039tok/sQ8_0
Phi-4 14Boffload24tok/sQ8_0
Qwen 3.5 4B99tok/sQ8_094tok/sQ8_0
Ministral 3 8B41tok/sQ8_039tok/sQ8_0
Granite 4.2 8B38tok/sQ8_036tok/sQ8_0
Gemma 4 E4B61tok/sQ8_058tok/sQ8_0
LFM2.5 8B-A1B125tok/sQ8_0118tok/sQ8_0
Llama 3.1 8B51tok/sQ6_K49tok/sQ6_K
Qwen2.5 0.5B595tok/sQ8_0566tok/sQ8_0
Qwen3.5 0.8B450tok/sQ8_0428tok/sQ8_0
Qwen3.5 2B299tok/sQ5_K_M284tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B196tok/sQ8_0186tok/sQ8_0
MiniCPM5 2B136tok/sQ8_0129tok/sQ8_0
LFM2.5 2.6B114tok/sQ8_0108tok/sQ8_0
LFM2.5 VL 3B114tok/sQ8_0108tok/sQ8_0
Mellum2.1 12B A2.5B Thinking105tok/sQ8_0100tok/sQ8_0
Kimi VL A3B94tok/smlx-6bit74tok/smlx-8bit
granite vision 4.1 4b88tok/sQ8_084tok/sQ8_0
granite 4.2 3b85tok/sQ8_080tok/sQ8_0
DeepSeek R1 Distill Qwen 7B56tok/sQ8_053tok/sQ8_0
GLM 4.6V Flash49tok/sQ8_047tok/sQ8_0
DeepSeek R1 Distill Llama 8B43tok/sQ8_041tok/sQ8_0
GLM 4.1V 9B Thinking42tok/smlx-8bit40tok/smlx-8bit
Ministral 3 8B Reasoning 251241tok/sQ8_039tok/sQ8_0
DeepSeek R1 Distill Qwen 14B36tok/sQ4_K_M24tok/sQ8_0
LFM2.5 24B A2Boffload71tok/sQ6_K
Devstral Small 2507offload24tok/sQ5_K_M
Magistral Small 2506offload24tok/sQ5_K_M
Magistral Small 2507offload24tok/sQ5_K_M
Magistral Small 2509offload24tok/sQ5_K_M
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
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 V3 0324won't runwon't run
DeepSeek V3.1won'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 4.6Vwon'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 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 NVIDIA GeForce RTX 5070 Ti or the AMD Radeon RX 7900 XTX?
Choose the AMD Radeon RX 7900 XTX to run bigger models. Choose the NVIDIA GeForce RTX 5070 Ti for speed. Choose the NVIDIA GeForce RTX 5070 Ti to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 5070 Ti or the AMD Radeon RX 7900 XTX?
At 32k context the AMD Radeon RX 7900 XTX runs 48 of the models we track fully in memory and the NVIDIA GeForce RTX 5070 Ti 30; only the AMD Radeon RX 7900 XTX holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 5070 Ti or the AMD Radeon RX 7900 XTX?
On the models both run fully in memory, the NVIDIA GeForce RTX 5070 Ti is about 1.1× as fast as the AMD Radeon RX 7900 XTX (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 5070 Ti and the AMD Radeon RX 7900 XTX?
In Canada the NVIDIA GeForce RTX 5070 Ti costs $1,650 at eBay and the AMD Radeon RX 7900 XTX $2,500 at eBay (used): the NVIDIA GeForce RTX 5070 Ti is $850 cheaper.

More comparisons