readygpu

NVIDIA RTX PRO 6000 Blackwell vs AMD Radeon RX 7900 XT

For running models locally, priced in Canada. At 128k context the first runs 70 models fully in memory, the second 24.

In short

The NVIDIA RTX PRO 6000 Blackwell has more memory for models: 96 GB against 20 GB. At 128k context the NVIDIA RTX PRO 6000 Blackwell runs 70 of the models we track fully in memory and the AMD Radeon RX 7900 XT 24; only the NVIDIA RTX PRO 6000 Blackwell holds Qwen 3.8 Flash Next. On the models both run fully in memory, the NVIDIA RTX PRO 6000 Blackwell is about 2.5× as fast as the AMD Radeon RX 7900 XT (estimated, median across models). In Canada the NVIDIA RTX PRO 6000 Blackwell costs $3,255 at Amazon and the AMD Radeon RX 7900 XT $1,200 at eBay: the AMD Radeon RX 7900 XT is $2,055 cheaper.

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

NVIDIA RTX PRO 6000 Blackwell

$3,255

Amazon

Add to build
AMD Radeon RX 7900 XT

$1,200

eBay

Add to build

Specifications

SpecNVIDIA RTX PRO 6000 BlackwellAMD Radeon RX 7900 XT
GPURTX PRO 6000 BlackwellRadeon RX 7900 XT
Memory96 GB GDDR720 GB GDDR6
Memory bus512-bit320-bit
Memory bandwidth1,792 GB/s800 GB/s
FP16 compute504 TFLOPS103 TFLOPS
SoftwareCUDAROCm
Board power600 W315 W
PCIe generationGen 5Gen 4
PCIe lanesx16x16

What each runs

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

ModelNVIDIA RTX PRO 6000 BlackwellAMD Radeon RX 7900 XT
Qwen 3.8 Flash Next20tok/sUD-Q3_K_XLwon't run
Qwen 3.8 27B29tok/sQ8_0offload
Qwen 3.5 122B-A10B62tok/sQ5_K_Moffload
Qwen 3.6 27B30tok/sQ8_0offload
Qwen3 Coder Next90tok/sQ8_0won't run
gpt-oss 120B84tok/sMXFP4won't run
Nemotron 3 Super 120B-A12B63tok/sQ5_K_Mwon't run
Gemma 4 31B25tok/sQ8_0offload
Mistral Small 4 119B76tok/sQ6_Koffload
Qwen 3.6 35B-A3B114tok/sQ8_0offload
Qwen 3.5 27B30tok/sQ8_0offload
Gemma 4 26B-A4B95tok/sQ8_0offload
GLM 4.5 Air20tok/sQ4_K_Mwon't run
Qwen 3.5 35B-A3B114tok/sQ8_0offload
Qwen3 Next 80B-A3B104tok/sQ8_0won't run
GLM 4.7 Flash54tok/sQ8_0offload
Devstral Small 2 24B24tok/sQ8_0offload
Nemotron 3.5 Lightning 30B-A3B160tok/sUD-Q6_K_XLoffload
Kimi Linear 48B-A3B155tok/sQ8_0offload
gpt-oss 20B118tok/sMXFP447tok/sMXFP4
Qwen3 Coder 30B-A3B42tok/sQ8_0offload
Qwen3 32B16tok/sQ8_0won't run
Gemma 4 12B73tok/sQ8_029tok/sQ8_0
Qwen 3.5 9B80tok/sQ8_032tok/sQ8_0
Gemma 3 27B28tok/sQ8_0offload
Mistral Small 3.2 24B24tok/sQ8_0offload
DeepSeek R1 Distill Qwen 32B16tok/sQ8_0won't run
Llama 3.3 70B12tok/sQ5_K_Mwon't run
Ministral 3 14B31tok/sQ8_0offload
Qwen3 14B30tok/sQ8_0offload
DeepSeek R1 0528 Qwen3 8B40tok/sQ8_0offload
Qwen3 8B40tok/sQ8_0offload
Phi-4 14B26tok/sQ8_0offload
Qwen 3.5 4B126tok/sQ8_050tok/sQ8_0
Ministral 3 8B41tok/sQ8_0offload
Granite 4.2 8B36tok/sQ8_0offload
Gemma 4 E4B93tok/sQ8_037tok/sQ8_0
LFM2.5 8B-A1B89tok/sQ8_035tok/sQ8_0
Llama 3.1 8B47tok/sQ6_Koffload
Qwen2.5 0.5B519tok/sQ8_0205tok/sQ8_0
Qwen3.5 0.8B455tok/sQ8_0180tok/sQ8_0
Qwen3.5 2B363tok/sQ5_K_M144tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B197tok/sQ8_078tok/sQ8_0
Mellum2.1 12B A2.5B Thinking146tok/sQ8_058tok/sQ8_0
Spark X2.5 4B140tok/smlx-4bit56tok/smlx-4bit
MiniCPM5 2B134tok/sQ8_053tok/sQ8_0
FrogNano 4B 2609124tok/sQ8_049tok/sQ8_0
LFM2.5 2.6B102tok/sQ8_040tok/sQ8_0
LFM2.5 VL 3B102tok/sQ8_040tok/sQ8_0
Kimi VL A3B Thinking 250693tok/sQ8_044tok/sQ4_K_M
Kimi VL A3B91tok/smlx-8bit40tok/smlx-6bit
GLM 4 9B 041482tok/smlx-5bit32tok/smlx-5bit
granite vision 4.1 4b77tok/sQ8_031tok/sQ8_0
granite 4.2 3b76tok/sQ8_030tok/sQ8_0
GLM 4.6V Flash72tok/sQ8_029tok/sQ8_0
DeepSeek R1 Distill Qwen 7B71tok/sQ8_028tok/sQ8_0
GLM 4.1V 9B Thinking65tok/smlx-8bit26tok/smlx-8bit
LFM2.5 24B A2B52tok/sQ8_0offload
DeepSeek R1 Distill Llama 8B43tok/sQ8_0offload
Ministral 3 8B Reasoning 251241tok/sQ8_0offload
Qwen3.8 27B OBLITERATED38tok/smlx-4bitoffload
DeepSeek R1 Distill Qwen 14B27tok/sQ8_0offload
Devstral Small 250724tok/sQ8_0offload
Magistral Small 250624tok/sQ8_0offload
Magistral Small 250724tok/sQ8_0offload
Magistral Small 250924tok/sQ8_0offload
GLM 4.5V20tok/sQ4_K_Mwon't run
GLM 4.6V20tok/sQ4_K_Mwon't run
granite 4.2 30b17tok/sQ8_0won't run
DeepSeek R1 Distill Llama 70B12tok/sQ5_K_Mwon't run
DeepSeek V4 Flashoffloadwon't run
GLM 5.3 Flashoffloadwon't run
MiniMax M2.7offloadwon't run
Kimi Dev 72Boffloadwon't run
Devstral 2 123B Instruct 2512offloadwon't run
Mistral Medium 3.5 128Boffloadwon'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
GLM 4.5won't runwon't run
GLM 4.6won'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 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

Questions

Which is better for local AI, the NVIDIA RTX PRO 6000 Blackwell or the AMD Radeon RX 7900 XT?
Choose the NVIDIA RTX PRO 6000 Blackwell to run bigger models. Choose the NVIDIA RTX PRO 6000 Blackwell for speed. Choose the AMD Radeon RX 7900 XT to spend less.
Which can run bigger models, the NVIDIA RTX PRO 6000 Blackwell or the AMD Radeon RX 7900 XT?
At 128k context the NVIDIA RTX PRO 6000 Blackwell runs 70 of the models we track fully in memory and the AMD Radeon RX 7900 XT 24; only the NVIDIA RTX PRO 6000 Blackwell holds Qwen 3.8 Flash Next.
Which is faster for local AI, the NVIDIA RTX PRO 6000 Blackwell or the AMD Radeon RX 7900 XT?
On the models both run fully in memory, the NVIDIA RTX PRO 6000 Blackwell is about 2.5× as fast as the AMD Radeon RX 7900 XT (estimated, median across models).
What is the price difference between the NVIDIA RTX PRO 6000 Blackwell and the AMD Radeon RX 7900 XT?
In Canada the NVIDIA RTX PRO 6000 Blackwell costs $3,255 at Amazon and the AMD Radeon RX 7900 XT $1,200 at eBay: the AMD Radeon RX 7900 XT is $2,055 cheaper.

More comparisons