AMD Radeon AI PRO R9700 vs NVIDIA RTX PRO 6000 Blackwell

For running models locally, priced in Canada. At 8k context the first runs 29 models fully in memory, the second 41.

In short

The NVIDIA RTX PRO 6000 Blackwell has more memory for models: 96 GB against 32 GB. At 8k context the NVIDIA RTX PRO 6000 Blackwell runs 41 of the models we track fully in memory and the AMD Radeon AI PRO R9700 29; only the NVIDIA RTX PRO 6000 Blackwell holds DeepSeek V4 Flash. On the models both run fully in memory, the NVIDIA RTX PRO 6000 Blackwell is about 3.2× as fast as the AMD Radeon AI PRO R9700 (estimated, median across models). In Canada the AMD Radeon AI PRO R9700 costs $2,800 at Amazon and the NVIDIA RTX PRO 6000 Blackwell $3,133 at Amazon: the AMD Radeon AI PRO R9700 is $333 cheaper.

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

Specifications

SpecAMD Radeon AI PRO R9700NVIDIA RTX PRO 6000 Blackwell
GPURadeon AI PRO R9700RTX PRO 6000 Blackwell
Memory32 GB GDDR696 GB GDDR7
Memory bus256-bit512-bit
Memory bandwidth640 GB/s1,792 GB/s
FP16 compute191 TFLOPS504 TFLOPS
SoftwareROCmCUDA
Board power300 W600 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 AI PRO R9700NVIDIA RTX PRO 6000 Blackwell
DeepSeek V4 Flashwon't run89tok/sUD-Q2_K_XL
Qwen 3.8 Flash Nextwon't run21tok/sUD-Q3_K_XL
Qwen 3.8 27B12tok/sQ8_037tok/sQ8_0
MiniMax M2.7won't run117tok/sUD-Q2_K_XL
Qwen 3.5 122B-A10Boffload79tok/sQ6_K
Qwen 3.6 27B12tok/sQ8_038tok/sQ8_0
Gemma 4 31B13tok/sQ6_K33tok/sQ8_0
Qwen3 Coder Nextoffload151tok/sQ8_0
Nemotron 3 Super 120B-A12Boffload81tok/sUD-Q4_K_M
gpt-oss 120Bwon't run195tok/sMXFP4
Mistral Small 4 119Boffload110tok/sUD-Q6_K
Qwen 3.6 35B-A3B79tok/sUD-Q6_K201tok/sQ8_0
Qwen 3.5 27B12tok/sQ8_038tok/sQ8_0
Gemma 4 26B-A4B47tok/sQ8_0147tok/sQ8_0
GLM 4.5 Airoffload40tok/sQ6_K
Qwen 3.5 35B-A3B80tok/sQ6_K201tok/sQ8_0
GLM 4.7 Flash37tok/sQ8_0117tok/sQ8_0
Devstral Small 2 24B13tok/sQ8_042tok/sQ8_0
Qwen3 Next 80B-A3Boffload196tok/sQ8_0
Nemotron 3.5 Lightning 30B-A3Boffload195tok/sUD-Q6_K_XL
Kimi Linear 48B-A3B109tok/sQ4_K_M202tok/sQ8_0
gpt-oss 20B80tok/sMXFP4253tok/sMXFP4
Qwen3 Coder 30B-A3B65tok/sQ6_K167tok/sQ8_0
Qwen3 32B12tok/sQ6_K30tok/sQ8_0
Gemma 4 12B27tok/sQ8_085tok/sQ8_0
Qwen 3.5 9B36tok/sQ8_0113tok/sQ8_0
Mistral Small 3.2 24B13tok/sQ8_042tok/sQ8_0
DeepSeek R1 Distill Qwen 32B12tok/sQ6_K30tok/sQ8_0
Gemma 3 27B12tok/sQ8_037tok/sQ8_0
Llama 3.3 70Boffload14tok/sQ8_0
Ministral 3 14B22tok/sQ8_071tok/sQ8_0
Qwen3 14B21tok/sQ8_065tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B36tok/sQ8_0112tok/sQ8_0
Qwen3 8B36tok/sQ8_0112tok/sQ8_0
Phi-4 14B20tok/sQ8_064tok/sQ8_0
Qwen 3.5 4B73tok/sQ8_0231tok/sQ8_0
Ministral 3 8B35tok/sQ8_0109tok/sQ8_0
Granite 4.2 8B33tok/sQ8_0104tok/sQ8_0
Gemma 4 E4B42tok/sQ8_0131tok/sQ8_0
LFM2.5 8B-A1B144tok/sQ8_0455tok/sQ8_0
Llama 3.1 8B46tok/sQ6_K145tok/sQ6_K
GLM 5.3 Flashwon't runoffload

Questions

Which is better for local AI, the AMD Radeon AI PRO R9700 or the NVIDIA RTX PRO 6000 Blackwell?
Choose the NVIDIA RTX PRO 6000 Blackwell to run bigger models. Choose the NVIDIA RTX PRO 6000 Blackwell for speed. Choose the AMD Radeon AI PRO R9700 to spend less.
Which can run bigger models, the AMD Radeon AI PRO R9700 or the NVIDIA RTX PRO 6000 Blackwell?
At 8k context the NVIDIA RTX PRO 6000 Blackwell runs 41 of the models we track fully in memory and the AMD Radeon AI PRO R9700 29; only the NVIDIA RTX PRO 6000 Blackwell holds DeepSeek V4 Flash.
Which is faster for local AI, the AMD Radeon AI PRO R9700 or the NVIDIA RTX PRO 6000 Blackwell?
On the models both run fully in memory, the NVIDIA RTX PRO 6000 Blackwell is about 3.2× 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 NVIDIA RTX PRO 6000 Blackwell?
In Canada the AMD Radeon AI PRO R9700 costs $2,800 at Amazon and the NVIDIA RTX PRO 6000 Blackwell $3,133 at Amazon: the AMD Radeon AI PRO R9700 is $333 cheaper.

More comparisons