readygpu

AMD Radeon RX 9070 vs AMD Radeon RX 9070 XT

For running models locally, priced in Canada. At 8k context the first runs 37 models fully in memory, the second 37.

In short

Both have 16 GB of memory for models; the AMD Radeon RX 9070 has 640 GB/s of bandwidth and the AMD Radeon RX 9070 XT 640 GB/s. At 8k context both run the same 37 models we track fully in memory. On the models both run fully in memory, the AMD Radeon RX 9070 and the AMD Radeon RX 9070 XT are about as fast as each other (estimated). In Canada the AMD Radeon RX 9070 costs $1,074 at Amazon and the AMD Radeon RX 9070 XT $1,050 at Amazon: the AMD Radeon RX 9070 XT is $24 cheaper.

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

AMD Radeon RX 9070

$1,074

Amazon

Add to build
AMD Radeon RX 9070 XT

$1,050

Amazon

Add to build

Specifications

SpecAMD Radeon RX 9070AMD Radeon RX 9070 XT
GPURadeon RX 9070Radeon RX 9070 XT
Memory16 GB GDDR616 GB GDDR6
Memory bus256-bit256-bit
Memory bandwidth640 GB/s640 GB/s
FP16 compute36.1 TFLOPS195 TFLOPS
SoftwareROCmROCm
Board power220 W304 W
PCIe generationGen 5Gen 5
PCIe lanesx16x16

What each runs

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

ModelAMD Radeon RX 9070AMD Radeon RX 9070 XT
gpt-oss 20B80tok/sMXFP480tok/sMXFP4
Gemma 4 12B27tok/sQ8_027tok/sQ8_0
Qwen 3.5 9B36tok/sQ8_036tok/sQ8_0
Ministral 3 14B28tok/sQ6_K28tok/sQ6_K
Qwen3 14B26tok/sQ6_K26tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B36tok/sQ8_036tok/sQ8_0
Qwen3 8B36tok/sQ8_036tok/sQ8_0
Phi-4 14B26tok/sQ6_K26tok/sQ6_K
Qwen 3.5 4B73tok/sQ8_073tok/sQ8_0
Ministral 3 8B35tok/sQ8_035tok/sQ8_0
Granite 4.2 8B33tok/sQ8_033tok/sQ8_0
Gemma 4 E4B42tok/sQ8_042tok/sQ8_0
LFM2.5 8B-A1B144tok/sQ8_0144tok/sQ8_0
Llama 3.1 8B46tok/sQ6_K46tok/sQ6_K
Qwen2.5 0.5B557tok/sQ8_0557tok/sQ8_0
Qwen3.5 0.8B378tok/sQ8_0378tok/sQ8_0
Qwen3.5 2B226tok/sQ5_K_M226tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B165tok/sQ8_0165tok/sQ8_0
MiniCPM5 2B116tok/sQ8_0116tok/sQ8_0
LFM2.5 2.6B104tok/sQ8_0104tok/sQ8_0
LFM2.5 VL 3B104tok/sQ8_0104tok/sQ8_0
Spark X2.5 4B104tok/smlx-4bit104tok/smlx-4bit
Kimi VL A3B Thinking 250697tok/sQ4_K_M97tok/sQ4_K_M
granite vision 4.1 4b82tok/sQ8_082tok/sQ8_0
Ministral 3 3B Instruct 251278tok/sQ8_078tok/sQ8_0
granite 4.2 3b77tok/sQ8_077tok/sQ8_0
Kimi VL A3B76tok/smlx-6bit76tok/smlx-6bit
Mellum2.1 12B A2.5B Thinking75tok/sQ8_075tok/sQ8_0
FrogNano 4B 260971tok/sQ8_071tok/sQ8_0
DeepSeek R1 Distill Qwen 7B41tok/sQ8_041tok/sQ8_0
GLM 4 9B 041441tok/smlx-5bit41tok/smlx-5bit
DeepSeek R1 Distill Llama 8B37tok/sQ8_037tok/sQ8_0
Ministral 3 8B Reasoning 251235tok/sQ8_035tok/sQ8_0
GLM 4.6V Flash34tok/sQ8_034tok/sQ8_0
GLM 4.1V 9B Thinking29tok/smlx-8bit29tok/smlx-8bit
Ministral 3 14B Reasoning 251228tok/sQ6_K28tok/sQ6_K
DeepSeek R1 Distill Qwen 14B26tok/sQ6_K26tok/sQ6_K
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Boffloadoffload
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadoffload
Qwen 3.6 35B-A3Boffloadoffload
Qwen 3.5 27Boffloadoffload
Gemma 4 26B-A4Boffloadoffload
Qwen 3.5 35B-A3Boffloadoffload
GLM 4.7 Flashoffloadoffload
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
Gemma 3 27Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
LFM2.5 24B A2Boffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
Muse Glimmer 30Boffloadoffload
granite 4.2 30boffloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
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 9070 or the AMD Radeon RX 9070 XT?
Choose the AMD Radeon RX 9070 XT to spend less.
Which can run bigger models, the AMD Radeon RX 9070 or the AMD Radeon RX 9070 XT?
At 8k context both run the same 37 models we track fully in memory.
Which is faster for local AI, the AMD Radeon RX 9070 or the AMD Radeon RX 9070 XT?
On the models both run fully in memory, the AMD Radeon RX 9070 and the AMD Radeon RX 9070 XT are about as fast as each other (estimated).
What is the price difference between the AMD Radeon RX 9070 and the AMD Radeon RX 9070 XT?
In Canada the AMD Radeon RX 9070 costs $1,074 at Amazon and the AMD Radeon RX 9070 XT $1,050 at Amazon: the AMD Radeon RX 9070 XT is $24 cheaper.

More comparisons

More hardware for local AI