readygpu

NVIDIA RTX PRO 2000 Blackwell vs AMD Radeon RX 7600 XT

For running models locally, priced in Canada. At 8k context the first runs 44 models fully in memory, the second 38.

In short

Both have 16 GB of memory for models; the NVIDIA RTX PRO 2000 Blackwell has 288 GB/s of bandwidth and the AMD Radeon RX 7600 XT 288 GB/s. At 8k context the NVIDIA RTX PRO 2000 Blackwell runs 44 of the models we track fully in memory and the AMD Radeon RX 7600 XT 38; only the NVIDIA RTX PRO 2000 Blackwell holds Devstral Small 2 24B. On the models both run fully in memory, the NVIDIA RTX PRO 2000 Blackwell is about 1.1× as fast as the AMD Radeon RX 7600 XT (estimated, median across models). In Canada the NVIDIA RTX PRO 2000 Blackwell costs $2,241 at Amazon and the AMD Radeon RX 7600 XT $1,419 at Amazon: the AMD Radeon RX 7600 XT is $822 cheaper.

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

NVIDIA RTX PRO 2000 Blackwell

$2,241

Amazon

Add to build
AMD Radeon RX 7600 XT

$1,419

Amazon

Add to build

Specifications

SpecNVIDIA RTX PRO 2000 BlackwellAMD Radeon RX 7600 XT
GPURTX PRO 2000 BlackwellRadeon RX 7600 XT
Memory16 GB GDDR716 GB GDDR6
Memory bus128-bit128-bit
Memory bandwidth288 GB/s288 GB/s
FP16 compute17.03 TFLOPS45 TFLOPS
SoftwareCUDAROCm
Board power70 W190 W
PCIe generationGen 5Gen 4
PCIe lanesx8x8

What each runs

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

ModelNVIDIA RTX PRO 2000 BlackwellAMD Radeon RX 7600 XT
Devstral Small 2 24B11tok/sQ4_K_Moffload
gpt-oss 20B41tok/sMXFP436tok/sMXFP4
Gemma 4 12B14tok/sQ8_012tok/sQ8_0
Qwen 3.5 9B18tok/sQ8_016tok/sQ8_0
Mistral Small 3.2 24B11tok/sQ4_K_Moffload
Qwen3 14B13tok/sQ6_K12tok/sQ6_K
Ministral 3 14B11tok/sQ8_013tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B18tok/sQ8_016tok/sQ8_0
Qwen3 8B18tok/sQ8_016tok/sQ8_0
Phi-4 14B13tok/sQ6_K12tok/sQ6_K
Qwen 3.5 4B37tok/sQ8_033tok/sQ8_0
Ministral 3 8B18tok/sQ8_016tok/sQ8_0
Granite 4.2 8B17tok/sQ8_015tok/sQ8_0
Gemma 4 E4B21tok/sQ8_019tok/sQ8_0
LFM2.5 8B-A1B73tok/sQ8_065tok/sQ8_0
Llama 3.1 8B23tok/sQ6_K21tok/sQ6_K
Qwen2.5 0.5B283tok/sQ8_0251tok/sQ8_0
Qwen3.5 0.8B192tok/sQ8_0170tok/sQ8_0
Qwen3.5 2B115tok/sQ5_K_M102tok/sQ5_K_M
LFM3 1.7B91tok/sQ8_081tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B84tok/sQ8_074tok/sQ8_0
MiniCPM5 2B59tok/sQ8_052tok/sQ8_0
LFM2.5 2.6B53tok/sQ8_047tok/sQ8_0
LFM2.5 VL 3B53tok/sQ8_047tok/sQ8_0
Spark X2.5 4B53tok/smlx-4bit47tok/smlx-4bit
Kimi VL A3B Thinking 250649tok/sQ4_K_M44tok/sQ4_K_M
granite vision 4.1 4b42tok/sQ8_037tok/sQ8_0
Ministral 3 3B Instruct 251240tok/sQ8_035tok/sQ8_0
granite 4.2 3b39tok/sQ8_035tok/sQ8_0
Kimi VL A3B39tok/smlx-6bit34tok/smlx-6bit
Mellum2.1 12B A2.5B Thinking38tok/sQ8_034tok/sQ8_0
FrogNano 4B 260936tok/sQ8_032tok/sQ8_0
DeepSeek R1 Distill Qwen 7B21tok/sQ8_019tok/sQ8_0
GLM 4 9B 041421tok/smlx-5bit19tok/smlx-5bit
DeepSeek R1 Distill Llama 8B19tok/sQ8_017tok/sQ8_0
Ministral 3 8B Reasoning 251218tok/sQ8_016tok/sQ8_0
GLM 4.6V Flash17tok/sQ8_015tok/sQ8_0
GLM 4.1V 9B Thinking15tok/smlx-8bit13tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B13tok/sQ6_K12tok/sQ6_K
Devstral Small 250711tok/sQ4_K_Moffload
Magistral Small 250611tok/sQ4_K_Moffload
Magistral Small 250711tok/sQ4_K_Moffload
Magistral Small 250911tok/sQ4_K_Moffload
Ministral 3 14B Reasoning 251211tok/sQ8_013tok/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
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Gemma 3 27Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
LFM2.5 24B A2Boffloadoffload
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 NVIDIA RTX PRO 2000 Blackwell or the AMD Radeon RX 7600 XT?
Choose the NVIDIA RTX PRO 2000 Blackwell to run bigger models. Choose the NVIDIA RTX PRO 2000 Blackwell for speed. Choose the AMD Radeon RX 7600 XT to spend less.
Which can run bigger models, the NVIDIA RTX PRO 2000 Blackwell or the AMD Radeon RX 7600 XT?
At 8k context the NVIDIA RTX PRO 2000 Blackwell runs 44 of the models we track fully in memory and the AMD Radeon RX 7600 XT 38; only the NVIDIA RTX PRO 2000 Blackwell holds Devstral Small 2 24B.
Which is faster for local AI, the NVIDIA RTX PRO 2000 Blackwell or the AMD Radeon RX 7600 XT?
On the models both run fully in memory, the NVIDIA RTX PRO 2000 Blackwell is about 1.1× as fast as the AMD Radeon RX 7600 XT (estimated, median across models).
What is the price difference between the NVIDIA RTX PRO 2000 Blackwell and the AMD Radeon RX 7600 XT?
In Canada the NVIDIA RTX PRO 2000 Blackwell costs $2,241 at Amazon and the AMD Radeon RX 7600 XT $1,419 at Amazon: the AMD Radeon RX 7600 XT is $822 cheaper.

More comparisons

More hardware for local AI