readygpu

NVIDIA GeForce RTX 3090 vs NVIDIA RTX PRO 2000 Blackwell

For running models locally, priced in the US. At 128k context the first runs 32 models fully in memory, the second 23.

In short

The NVIDIA GeForce RTX 3090 has more memory for models: 24 GB against 16 GB. At 128k context the NVIDIA GeForce RTX 3090 runs 32 of the models we track fully in memory and the NVIDIA RTX PRO 2000 Blackwell 23; only the NVIDIA GeForce RTX 3090 holds Gemma 4 26B-A4B. On the models both run fully in memory, the NVIDIA GeForce RTX 3090 is about 3.2× as fast as the NVIDIA RTX PRO 2000 Blackwell (estimated, median across models). In the US the NVIDIA GeForce RTX 3090 costs $1,698 at Amazon and the NVIDIA RTX PRO 2000 Blackwell $1,580 at eBay: the NVIDIA RTX PRO 2000 Blackwell is $118 cheaper.

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

NVIDIA GeForce RTX 3090

$1,698

Amazon

Add to build
NVIDIA RTX PRO 2000 Blackwell

$1,580

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 3090NVIDIA RTX PRO 2000 Blackwell
GPUGeForce RTX 3090RTX PRO 2000 Blackwell
Memory24 GB GDDR6X16 GB GDDR7
Memory bus384-bit128-bit
Memory bandwidth936 GB/s288 GB/s
FP16 compute71 TFLOPS17.03 TFLOPS
SoftwareCUDACUDA
Board power350 W70 W
PCIe generationGen 4Gen 5
PCIe lanesx16x8

What each runs

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

ModelNVIDIA GeForce RTX 3090NVIDIA RTX PRO 2000 Blackwell
Gemma 4 26B-A4B59tok/sQ5_K_Moffload
gpt-oss 20B62tok/sMXFP419tok/sQ4_K_M
Gemma 4 12B38tok/sQ8_015tok/sQ6_K
Qwen 3.5 9B42tok/sQ8_013tok/sQ8_0
Qwen 3.5 4B66tok/sQ8_020tok/sQ8_0
Ministral 3 8B25tok/sQ4_K_Moffload
Gemma 4 E4B48tok/sQ8_015tok/sQ8_0
LFM2.5 8B-A1B46tok/sQ8_015tok/sUD-Q6_K
Llama 3.1 8B25tok/sQ5_K_Moffload
Qwen2.5 0.5B271tok/sQ8_083tok/sQ8_0
Qwen3.5 0.8B238tok/sQ8_073tok/sQ8_0
Qwen3.5 2B189tok/sQ5_K_M58tok/sQ5_K_M
LFM3 1.7B167tok/sQ8_052tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B103tok/sQ8_032tok/sQ8_0
Mellum2.1 12B A2.5B Thinking76tok/sQ8_023tok/sQ8_0
Spark X2.5 4B73tok/smlx-4bit23tok/smlx-4bit
MiniCPM5 2B70tok/sQ8_022tok/sQ8_0
FrogNano 4B 260965tok/sQ8_020tok/sQ8_0
LFM2.5 2.6B53tok/sQ8_016tok/sQ8_0
LFM2.5 VL 3B53tok/sQ8_016tok/sQ8_0
Kimi VL A3B Thinking 250649tok/sQ8_018tok/sQ4_K_M
Kimi VL A3B48tok/smlx-8bitoffload
GLM 4 9B 041443tok/smlx-5bit13tok/smlx-5bit
granite vision 4.1 4b40tok/sQ8_012tok/sQ8_0
granite 4.2 3b40tok/sQ8_012tok/sQ8_0
GLM 4.6V Flash38tok/sQ8_016tok/sQ4_K_M
DeepSeek R1 Distill Qwen 7B37tok/sQ8_013tok/sQ6_K
GLM 4.1V 9B Thinking34tok/smlx-8bitoffload
Ministral 3 3B Instruct 251233tok/sQ8_0offload
Muse Glimmer 30B27tok/sQ5_K_Moffload
DeepSeek R1 Distill Llama 8B25tok/sQ5_K_Moffload
Ministral 3 8B Reasoning 251225tok/sQ4_K_Moffload
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Boffloadwon't run
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadwon't run
Qwen 3.6 35B-A3Boffloadoffload
Qwen 3.5 27Boffloadoffload
Qwen 3.5 35B-A3Boffloadoffload
GLM 4.7 Flashoffloadoffload
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Gemma 3 27Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
Ministral 3 14Boffloadoffload
Qwen3 14Boffloadoffload
DeepSeek R1 0528 Qwen3 8Boffloadoffload
Qwen3 8Boffloadoffload
Phi-4 14Boffloadoffload
Granite 4.2 8Boffloadoffload
LFM2.5 24B A2Boffloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
Ministral 3 14B Reasoning 2512offloadoffload
DeepSeek R1 Distill Qwen 14Boffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
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
Qwen3 32Bwon't runwon't run
DeepSeek R1 Distill Qwen 32Bwon'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
granite 4.2 30bwon't runwon't run

Questions

Which is better for local AI, the NVIDIA GeForce RTX 3090 or the NVIDIA RTX PRO 2000 Blackwell?
Choose the NVIDIA GeForce RTX 3090 to run bigger models. Choose the NVIDIA GeForce RTX 3090 for speed. Choose the NVIDIA RTX PRO 2000 Blackwell to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 3090 or the NVIDIA RTX PRO 2000 Blackwell?
At 128k context the NVIDIA GeForce RTX 3090 runs 32 of the models we track fully in memory and the NVIDIA RTX PRO 2000 Blackwell 23; only the NVIDIA GeForce RTX 3090 holds Gemma 4 26B-A4B.
Which is faster for local AI, the NVIDIA GeForce RTX 3090 or the NVIDIA RTX PRO 2000 Blackwell?
On the models both run fully in memory, the NVIDIA GeForce RTX 3090 is about 3.2× as fast as the NVIDIA RTX PRO 2000 Blackwell (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 3090 and the NVIDIA RTX PRO 2000 Blackwell?
In the US the NVIDIA GeForce RTX 3090 costs $1,698 at Amazon and the NVIDIA RTX PRO 2000 Blackwell $1,580 at eBay: the NVIDIA RTX PRO 2000 Blackwell is $118 cheaper.

More comparisons

More hardware for local AI