readygpu

AMD Radeon AI PRO R9700 vs AMD Radeon RX 7900 XT

For running models locally, priced in Canada. At 8k context the first runs 58 models fully in memory, the second 49.

In short

The AMD Radeon AI PRO R9700 has more memory for models: 32 GB against 20 GB. At 8k context the AMD Radeon AI PRO R9700 runs 58 of the models we track fully in memory and the AMD Radeon RX 7900 XT 49; only the AMD Radeon AI PRO R9700 holds Gemma 4 31B. On the models both run fully in memory, the AMD Radeon RX 7900 XT is about 1.3× as fast as the AMD Radeon AI PRO R9700 (estimated, median across models). In Canada the AMD Radeon AI PRO R9700 costs $2,840 at Amazon and the AMD Radeon RX 7900 XT $1,200 at eBay: the AMD Radeon RX 7900 XT is $1,640 cheaper.

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

AMD Radeon AI PRO R9700

$2,840

Amazon

Add to build
AMD Radeon RX 7900 XT

$1,200

eBay

Add to build

Specifications

SpecAMD Radeon AI PRO R9700AMD Radeon RX 7900 XT
GPURadeon AI PRO R9700Radeon RX 7900 XT
Memory32 GB GDDR620 GB GDDR6
Memory bus256-bit320-bit
Memory bandwidth640 GB/s800 GB/s
FP16 compute191 TFLOPS103 TFLOPS
SoftwareROCmROCm
Board power300 W315 W
PCIe generationGen 5Gen 4
PCIe lanesx16x16

What each runs

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

ModelAMD Radeon AI PRO R9700AMD Radeon RX 7900 XT
Qwen 3.8 27B12tok/sQ8_024tok/sQ4_K_M
Qwen 3.6 27B12tok/sQ8_025tok/sQ4_K_M
Gemma 4 31B13tok/sQ6_Koffload
Qwen 3.6 35B-A3B75tok/sQ6_Koffload
Qwen 3.5 27B12tok/sQ8_025tok/sQ4_K_M
Gemma 4 26B-A4B47tok/sQ8_078tok/sQ5_K_M
Qwen 3.5 35B-A3B80tok/sQ6_Koffload
GLM 4.7 Flash37tok/sQ8_076tok/sQ4_K_M
Devstral Small 2 24B13tok/sQ8_024tok/sQ5_K_M
Nemotron 3.5 Lightning 30B-A3B71tok/sUD-Q5_K_Moffload
Kimi Linear 48B-A3B109tok/sQ4_K_Moffload
gpt-oss 20B80tok/sMXFP4100tok/sMXFP4
Qwen3 Coder 30B-A3B65tok/sQ6_K100tok/sQ4_K_M
Qwen3 32B12tok/sQ6_Koffload
Gemma 4 12B27tok/sQ8_034tok/sQ8_0
Qwen 3.5 9B36tok/sQ8_045tok/sQ8_0
Mistral Small 3.2 24B13tok/sQ8_024tok/sQ5_K_M
DeepSeek R1 Distill Qwen 32B12tok/sQ6_Koffload
Gemma 3 27B12tok/sQ8_025tok/sQ4_K_M
Ministral 3 14B22tok/sQ8_028tok/sQ8_0
Qwen3 14B21tok/sQ8_026tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B36tok/sQ8_044tok/sQ8_0
Qwen3 8B36tok/sQ8_044tok/sQ8_0
Phi-4 14B20tok/sQ8_026tok/sQ8_0
Qwen 3.5 4B73tok/sQ8_092tok/sQ8_0
Ministral 3 8B35tok/sQ8_043tok/sQ8_0
Granite 4.2 8B33tok/sQ8_041tok/sQ8_0
Gemma 4 E4B42tok/sQ8_052tok/sQ8_0
LFM2.5 8B-A1B144tok/sQ8_0180tok/sQ8_0
Llama 3.1 8B46tok/sQ6_K57tok/sQ6_K
Qwen2.5 0.5B557tok/sQ8_0697tok/sQ8_0
Qwen3.5 0.8B378tok/sQ8_0472tok/sQ8_0
Qwen3.5 2B226tok/sQ5_K_M283tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B165tok/sQ8_0207tok/sQ8_0
MiniCPM5 2B116tok/sQ8_0145tok/sQ8_0
LFM2.5 2.6B104tok/sQ8_0130tok/sQ8_0
LFM2.5 VL 3B104tok/sQ8_0130tok/sQ8_0
Spark X2.5 4B104tok/smlx-4bit130tok/smlx-4bit
granite vision 4.1 4b82tok/sQ8_0103tok/sQ8_0
granite 4.2 3b77tok/sQ8_096tok/sQ8_0
LFM2.5 24B A2B76tok/sQ8_0119tok/sQ5_K_M
Mellum2.1 12B A2.5B Thinking75tok/sQ8_094tok/sQ8_0
FrogNano 4B 260971tok/sQ8_089tok/sQ8_0
Kimi VL A3B Thinking 250663tok/sQ8_079tok/sQ8_0
Kimi VL A3B60tok/smlx-8bit75tok/smlx-8bit
DeepSeek R1 Distill Qwen 7B41tok/sQ8_051tok/sQ8_0
GLM 4 9B 041441tok/smlx-5bit51tok/smlx-5bit
DeepSeek R1 Distill Llama 8B37tok/sQ8_046tok/sQ8_0
Ministral 3 8B Reasoning 251235tok/sQ8_043tok/sQ8_0
GLM 4.6V Flash34tok/sQ8_043tok/sQ8_0
GLM 4.1V 9B Thinking29tok/smlx-8bit36tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B20tok/sQ8_025tok/sQ8_0
Qwen3.8 27B OBLITERATED17tok/smlx-4bitoffload
Devstral Small 250713tok/sQ8_024tok/sQ5_K_M
Magistral Small 250613tok/sQ8_024tok/sQ5_K_M
Magistral Small 250713tok/sQ8_024tok/sQ5_K_M
Magistral Small 250913tok/sQ8_024tok/sQ5_K_M
granite 4.2 30b13tok/sQ6_Koffload
Qwen 3.5 122B-A10Boffloadoffload
Qwen3 Coder Nextoffloadwon't run
Nemotron 3 Super 120B-A12Boffloadwon't run
Mistral Small 4 119Boffloadoffload
GLM 4.5 Airoffloadoffload
Qwen3 Next 80B-A3Boffloadwon't run
Llama 3.3 70Boffloadoffload
DeepSeek R1 Distill Llama 70Boffloadoffload
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
gpt-oss 120Bwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won'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 AI PRO R9700 or the AMD Radeon RX 7900 XT?
Choose the AMD Radeon AI PRO R9700 to run bigger models. Choose the AMD Radeon RX 7900 XT for speed. Choose the AMD Radeon RX 7900 XT to spend less.
Which can run bigger models, the AMD Radeon AI PRO R9700 or the AMD Radeon RX 7900 XT?
At 8k context the AMD Radeon AI PRO R9700 runs 58 of the models we track fully in memory and the AMD Radeon RX 7900 XT 49; only the AMD Radeon AI PRO R9700 holds Gemma 4 31B.
Which is faster for local AI, the AMD Radeon AI PRO R9700 or the AMD Radeon RX 7900 XT?
On the models both run fully in memory, the AMD Radeon RX 7900 XT is about 1.3× as fast as the AMD Radeon AI PRO R9700 (estimated, median across models).
What is the price difference between the AMD Radeon AI PRO R9700 and the AMD Radeon RX 7900 XT?
In Canada the AMD Radeon AI PRO R9700 costs $2,840 at Amazon and the AMD Radeon RX 7900 XT $1,200 at eBay: the AMD Radeon RX 7900 XT is $1,640 cheaper.

More comparisons