readygpu

NVIDIA GeForce RTX 4060 Ti 16GB vs NVIDIA RTX PRO 2000 Blackwell

For running models locally, priced in the UK. At 32k context the first runs 37 models fully in memory, the second 37.

In short

Both have 16 GB of memory for models; the NVIDIA GeForce RTX 4060 Ti 16GB has 288 GB/s of bandwidth and the NVIDIA RTX PRO 2000 Blackwell 288 GB/s. At 32k context both run the same 37 models we track fully in memory. On the models both run fully in memory, the NVIDIA GeForce RTX 4060 Ti 16GB and the NVIDIA RTX PRO 2000 Blackwell are about as fast as each other (estimated).

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

NVIDIA GeForce RTX 4060 Ti 16GB

Not priced here

Add to build
NVIDIA RTX PRO 2000 Blackwell

£1,100

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 4060 Ti 16GBNVIDIA RTX PRO 2000 Blackwell
GPUGeForce RTX 4060 Ti 16GBRTX PRO 2000 Blackwell
Memory16 GB GDDR616 GB GDDR7
Memory bus128-bit128-bit
Memory bandwidth288 GB/s288 GB/s
FP16 compute44 TFLOPS17.03 TFLOPS
SoftwareCUDACUDA
Board power165 W70 W
PCIe generationGen 4Gen 5
PCIe lanesx8x8

What each runs

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

ModelNVIDIA GeForce RTX 4060 Ti 16GBNVIDIA RTX PRO 2000 Blackwell
gpt-oss 20B33tok/sMXFP433tok/sMXFP4
Gemma 4 12B13tok/sQ8_013tok/sQ8_0
Qwen 3.5 9B17tok/sQ8_017tok/sQ8_0
Qwen3 14B12tok/sQ4_K_M12tok/sQ4_K_M
Ministral 3 14B12tok/sQ5_K_M12tok/sQ5_K_M
DeepSeek R1 0528 Qwen3 8B13tok/sQ8_013tok/sQ8_0
Qwen3 8B13tok/sQ8_013tok/sQ8_0
Qwen 3.5 4B32tok/sQ8_032tok/sQ8_0
Ministral 3 8B13tok/sQ8_013tok/sQ8_0
Granite 4.2 8B12tok/sQ8_012tok/sQ8_0
Gemma 4 E4B20tok/sQ8_020tok/sQ8_0
LFM2.5 8B-A1B40tok/sQ8_040tok/sQ8_0
Llama 3.1 8B16tok/sQ6_K16tok/sQ6_K
Qwen2.5 0.5B191tok/sQ8_0191tok/sQ8_0
Qwen3.5 0.8B145tok/sQ8_0145tok/sQ8_0
Qwen3.5 2B96tok/sQ5_K_M96tok/sQ5_K_M
LFM3 1.7B79tok/sQ8_079tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B63tok/sQ8_063tok/sQ8_0
MiniCPM5 2B44tok/sQ8_044tok/sQ8_0
Spark X2.5 4B42tok/smlx-4bit42tok/smlx-4bit
LFM2.5 2.6B37tok/sQ8_037tok/sQ8_0
LFM2.5 VL 3B37tok/sQ8_037tok/sQ8_0
Kimi VL A3B Thinking 250636tok/sQ4_K_M36tok/sQ4_K_M
Mellum2.1 12B A2.5B Thinking34tok/sQ8_034tok/sQ8_0
FrogNano 4B 260931tok/sQ8_031tok/sQ8_0
Kimi VL A3B30tok/smlx-6bit30tok/smlx-6bit
granite vision 4.1 4b28tok/sQ8_028tok/sQ8_0
granite 4.2 3b27tok/sQ8_027tok/sQ8_0
Ministral 3 3B Instruct 251225tok/sQ8_025tok/sQ8_0
GLM 4 9B 041419tok/smlx-5bit19tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B18tok/sQ8_018tok/sQ8_0
GLM 4.6V Flash16tok/sQ8_016tok/sQ8_0
DeepSeek R1 Distill Llama 8B14tok/sQ8_014tok/sQ8_0
GLM 4.1V 9B Thinking14tok/smlx-8bit14tok/smlx-8bit
Ministral 3 8B Reasoning 251213tok/sQ8_013tok/sQ8_0
Ministral 3 14B Reasoning 251212tok/sQ5_K_M12tok/sQ5_K_M
DeepSeek R1 Distill Qwen 14B12tok/sQ4_K_M12tok/sQ4_K_M
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
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Gemma 3 27Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Phi-4 14Boffloadoffload
LFM2.5 24B A2Boffloadoffload
Muse Glimmer 30Boffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
granite 4.2 30boffloadoffload
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 can run bigger models, the NVIDIA GeForce RTX 4060 Ti 16GB or the NVIDIA RTX PRO 2000 Blackwell?
At 32k context both run the same 37 models we track fully in memory.
Which is faster for local AI, the NVIDIA GeForce RTX 4060 Ti 16GB or the NVIDIA RTX PRO 2000 Blackwell?
On the models both run fully in memory, the NVIDIA GeForce RTX 4060 Ti 16GB and the NVIDIA RTX PRO 2000 Blackwell are about as fast as each other (estimated).

More comparisons

More hardware for local AI