readygpu

AMD Radeon RX 7900 XT vs AMD Radeon RX 9070

For running models locally, priced in Canada. At 64k context the first runs 36 models fully in memory, the second 31.

In short

The AMD Radeon RX 7900 XT has more memory for models: 20 GB against 16 GB. At 64k context the AMD Radeon RX 7900 XT runs 36 of the models we track fully in memory and the AMD Radeon RX 9070 31; only the AMD Radeon RX 7900 XT holds Gemma 4 26B-A4B. On the models both run fully in memory, the AMD Radeon RX 7900 XT is about 1.2× as fast as the AMD Radeon RX 9070 (estimated, median across models). In Canada the AMD Radeon RX 7900 XT costs $3,035 at Amazon and the AMD Radeon RX 9070 $1,074 at Amazon: the AMD Radeon RX 9070 is $1,960 cheaper.

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

AMD Radeon RX 7900 XT

$3,035

Amazon

Add to build
AMD Radeon RX 9070

$1,074

Amazon

Add to build

Specifications

SpecAMD Radeon RX 7900 XTAMD Radeon RX 9070
GPURadeon RX 7900 XTRadeon RX 9070
Memory20 GB GDDR616 GB GDDR6
Memory bus320-bit256-bit
Memory bandwidth800 GB/s640 GB/s
FP16 compute103 TFLOPS36.1 TFLOPS
SoftwareROCmROCm
Board power315 W220 W
PCIe generationGen 4Gen 5
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 9070
Gemma 4 26B-A4B63tok/sQ4_K_Moffload
gpt-oss 20B65tok/sMXFP452tok/sMXFP4
Gemma 4 12B31tok/sQ8_025tok/sQ8_0
Qwen 3.5 9B38tok/sQ8_030tok/sQ8_0
Ministral 3 14B23tok/sQ4_K_Moffload
DeepSeek R1 0528 Qwen3 8B24tok/sQ8_024tok/sQ4_K_M
Qwen3 8B24tok/sQ8_024tok/sQ4_K_M
Qwen 3.5 4B66tok/sQ8_053tok/sQ8_0
Ministral 3 8B24tok/sQ8_025tok/sQ4_K_M
Granite 4.2 8B24tok/sQ6_Koffload
Gemma 4 E4B44tok/sQ8_035tok/sQ8_0
LFM2.5 8B-A1B62tok/sQ8_049tok/sQ8_0
Llama 3.1 8B29tok/sQ6_K25tok/sQ5_K_M
Qwen2.5 0.5B329tok/sQ8_0263tok/sQ8_0
Qwen3.5 0.8B269tok/sQ8_0215tok/sQ8_0
Qwen3.5 2B195tok/sQ5_K_M156tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B117tok/sQ8_093tok/sQ8_0
MiniCPM5 2B80tok/sQ8_064tok/sQ8_0
Spark X2.5 4B80tok/smlx-4bit64tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking73tok/sQ8_058tok/sQ8_0
FrogNano 4B 260965tok/sQ8_052tok/sQ8_0
LFM2.5 2.6B64tok/sQ8_051tok/sQ8_0
LFM2.5 VL 3B64tok/sQ8_051tok/sQ8_0
Kimi VL A3B58tok/smlx-6bit50tok/smlx-5bit
Kimi VL A3B Thinking 250651tok/sQ8_053tok/sQ4_K_M
granite vision 4.1 4b49tok/sQ8_039tok/sQ8_0
granite 4.2 3b48tok/sQ8_038tok/sQ8_0
Ministral 3 3B Instruct 251241tok/sQ8_033tok/sQ8_0
GLM 4 9B 041440tok/smlx-5bit32tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B37tok/sQ8_030tok/sQ8_0
GLM 4.6V Flash35tok/sQ8_028tok/sQ8_0
GLM 4.1V 9B Thinking30tok/smlx-8bit24tok/smlx-8bit
DeepSeek R1 Distill Llama 8B26tok/sQ8_025tok/sQ5_K_M
Ministral 3 8B Reasoning 251224tok/sQ8_025tok/sQ4_K_M
Muse Glimmer 30B24tok/sQ4_K_Moffload
Ministral 3 14B Reasoning 251223tok/sQ4_K_Moffload
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Boffloadwon't run
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadoffload
Qwen 3.6 35B-A3Boffloadoffload
Qwen 3.5 27Boffloadoffload
Qwen 3.5 35B-A3Boffloadoffload
GLM 4.7 Flashoffloadoffload
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Gemma 3 27Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Qwen3 14Boffloadoffload
Phi-4 14Boffloadoffload
LFM2.5 24B A2Boffloadoffload
DeepSeek R1 Distill Qwen 14Boffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
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
Qwen3 Coder Nextwon't runwon't run
gpt-oss 120Bwon't runwon't run
GLM 4.5 Airwon't runwon't run
Qwen3 Next 80B-A3Bwon'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 V3won'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 4.5won'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 5won'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 7900 XT or the AMD Radeon RX 9070?
Choose the AMD Radeon RX 7900 XT to run bigger models. Choose the AMD Radeon RX 7900 XT for speed. Choose the AMD Radeon RX 9070 to spend less.
Which can run bigger models, the AMD Radeon RX 7900 XT or the AMD Radeon RX 9070?
At 64k context the AMD Radeon RX 7900 XT runs 36 of the models we track fully in memory and the AMD Radeon RX 9070 31; only the AMD Radeon RX 7900 XT holds Gemma 4 26B-A4B.
Which is faster for local AI, the AMD Radeon RX 7900 XT or the AMD Radeon RX 9070?
On the models both run fully in memory, the AMD Radeon RX 7900 XT is about 1.2× as fast as the AMD Radeon RX 9070 (estimated, median across models).
What is the price difference between the AMD Radeon RX 7900 XT and the AMD Radeon RX 9070?
In Canada the AMD Radeon RX 7900 XT costs $3,035 at Amazon and the AMD Radeon RX 9070 $1,074 at Amazon: the AMD Radeon RX 9070 is $1,960 cheaper.

More comparisons

More hardware for local AI