readygpu

NVIDIA RTX PRO 6000 Blackwell vs AMD Radeon RX 7900 XT

For running models locally, priced in Canada. At 64k context the first runs 74 models fully in memory, the second 33.

In short

The NVIDIA RTX PRO 6000 Blackwell has more memory for models: 96 GB against 20 GB. At 64k context the NVIDIA RTX PRO 6000 Blackwell runs 74 of the models we track fully in memory and the AMD Radeon RX 7900 XT 33; 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 Next21tok/sUD-Q3_K_XLwon't run
Qwen 3.8 27B33tok/sQ8_0offload
MiniMax M2.733tok/sUD-Q2_K_XLwon't run
Qwen 3.5 122B-A10B73tok/sQ5_K_Moffload
Qwen 3.6 27B34tok/sQ8_0offload
gpt-oss 120B120tok/sMXFP4won't run
Qwen3 Coder Next115tok/sQ8_0won't run
Nemotron 3 Super 120B-A12B66tok/sQ5_K_Mwon't run
Gemma 4 31B29tok/sQ8_0offload
Mistral Small 4 119B90tok/sUD-Q6_Koffload
Qwen 3.6 35B-A3B149tok/sQ8_0offload
Qwen 3.5 27B34tok/sQ8_0offload
Gemma 4 26B-A4B117tok/sQ8_063tok/sQ4_K_M
GLM 4.5 Air29tok/sQ5_K_Mwon't run
Qwen 3.5 35B-A3B149tok/sQ8_0offload
Qwen3 Next 80B-A3B139tok/sQ8_0won't run
GLM 4.7 Flash76tok/sQ8_0offload
Devstral Small 2 24B31tok/sQ8_0offload
Nemotron 3.5 Lightning 30B-A3B177tok/sUD-Q6_K_XLoffload
Kimi Linear 48B-A3B177tok/sQ8_0offload
gpt-oss 20B165tok/sMXFP465tok/sMXFP4
Qwen3 Coder 30B-A3B69tok/sQ8_0offload
Qwen3 32B21tok/sQ8_0offload
Gemma 4 12B79tok/sQ8_031tok/sQ8_0
Qwen 3.5 9B95tok/sQ8_038tok/sQ8_0
Gemma 3 27B32tok/sQ8_0offload
Mistral Small 3.2 24B31tok/sQ8_0offload
DeepSeek R1 Distill Qwen 32B21tok/sQ8_0offload
Llama 3.3 70B12tok/sQ8_0won't run
Ministral 3 14B44tok/sQ8_023tok/sQ4_K_M
Qwen3 14B42tok/sQ8_0offload
DeepSeek R1 0528 Qwen3 8B61tok/sQ8_024tok/sQ8_0
Qwen3 8B61tok/sQ8_024tok/sQ8_0
Phi-4 14B38tok/sQ8_0offload
Qwen 3.5 4B166tok/sQ8_066tok/sQ8_0
Ministral 3 8B61tok/sQ8_024tok/sQ8_0
Granite 4.2 8B55tok/sQ8_024tok/sQ6_K
Gemma 4 E4B110tok/sQ8_044tok/sQ8_0
LFM2.5 8B-A1B156tok/sQ8_062tok/sQ8_0
Llama 3.1 8B73tok/sQ6_K29tok/sQ6_K
Qwen2.5 0.5B831tok/sQ8_0329tok/sQ8_0
Qwen3.5 0.8B679tok/sQ8_0269tok/sQ8_0
Qwen3.5 2B492tok/sQ5_K_M195tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B294tok/sQ8_0117tok/sQ8_0
MiniCPM5 2B202tok/sQ8_080tok/sQ8_0
Spark X2.5 4B202tok/smlx-4bit80tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking183tok/sQ8_073tok/sQ8_0
FrogNano 4B 2609163tok/sQ8_065tok/sQ8_0
LFM2.5 2.6B161tok/sQ8_064tok/sQ8_0
LFM2.5 VL 3B161tok/sQ8_064tok/sQ8_0
Kimi VL A3B Thinking 2506130tok/sQ8_051tok/sQ8_0
Kimi VL A3B126tok/smlx-8bit58tok/smlx-6bit
granite vision 4.1 4b124tok/sQ8_049tok/sQ8_0
granite 4.2 3b120tok/sQ8_048tok/sQ8_0
GLM 4 9B 0414102tok/smlx-5bit40tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B94tok/sQ8_037tok/sQ8_0
LFM2.5 24B A2B89tok/sQ8_0offload
GLM 4.6V Flash88tok/sQ8_035tok/sQ8_0
GLM 4.1V 9B Thinking77tok/smlx-8bit30tok/smlx-8bit
DeepSeek R1 Distill Llama 8B65tok/sQ8_026tok/sQ8_0
Ministral 3 8B Reasoning 251261tok/sQ8_024tok/sQ8_0
Qwen3.8 27B OBLITERATED44tok/smlx-4bitoffload
DeepSeek R1 Distill Qwen 14B39tok/sQ8_0offload
GLM 4.5V32tok/sQ4_K_Mwon't run
Devstral Small 250731tok/sQ8_0offload
Magistral Small 250631tok/sQ8_0offload
Magistral Small 250731tok/sQ8_0offload
Magistral Small 250931tok/sQ8_0offload
GLM 4.6V31tok/sQ4_K_Mwon't run
granite 4.2 30b23tok/sQ8_0offload
DeepSeek R1 Distill Llama 70B12tok/sQ8_0won't run
Devstral 2 123B Instruct 251211tok/sQ4_K_Mwon't run
Kimi Dev 72B11tok/sQ8_0won't run
Mistral Medium 3.5 128B11tok/sQ4_K_Mwon't run
DeepSeek V4 Flashoffloadwon't run
GLM 5.3 Flashoffloadwon'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 64k context the NVIDIA RTX PRO 6000 Blackwell runs 74 of the models we track fully in memory and the AMD Radeon RX 7900 XT 33; 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