readygpu

NVIDIA GeForce RTX 3060 12GB vs NVIDIA GeForce RTX 4060

For running models locally, priced in Canada. At 8k context the first runs 35 models fully in memory, the second 26.

In short

The NVIDIA GeForce RTX 3060 12GB has more memory for models: 12 GB against 8 GB. At 8k context the NVIDIA GeForce RTX 3060 12GB runs 35 of the models we track fully in memory and the NVIDIA GeForce RTX 4060 26; only the NVIDIA GeForce RTX 3060 12GB holds Gemma 4 12B. On the models both run fully in memory, the NVIDIA GeForce RTX 3060 12GB is about 1.3× as fast as the NVIDIA GeForce RTX 4060 (estimated, median across models). In Canada the NVIDIA GeForce RTX 3060 12GB costs $530 at Amazon and the NVIDIA GeForce RTX 4060 $839 at Amazon: the NVIDIA GeForce RTX 3060 12GB is $309 cheaper.

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

NVIDIA GeForce RTX 3060 12GB

$530

Amazon

Add to build
NVIDIA GeForce RTX 4060

$839

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 3060 12GBNVIDIA GeForce RTX 4060
GPUGeForce RTX 3060 12GBGeForce RTX 4060
Memory12 GB GDDR68 GB GDDR6
Memory bus192-bit128-bit
Memory bandwidth360 GB/s272 GB/s
FP16 compute25.6 TFLOPS15.114 TFLOPS
SoftwareCUDACUDA
Board power170 W115 W
PCIe generationGen 4Gen 4
PCIe lanesx16x8

What each runs

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

ModelNVIDIA GeForce RTX 3060 12GBNVIDIA GeForce RTX 4060
Gemma 4 12B22tok/sQ6_Koffload
Qwen 3.5 9B23tok/sQ8_025tok/sQ5_K_M
Qwen3 14B22tok/sQ4_K_Moffload
Ministral 3 14B20tok/sQ5_K_Moffload
DeepSeek R1 0528 Qwen3 8B23tok/sQ8_024tok/sQ5_K_M
Qwen3 8B23tok/sQ8_024tok/sQ5_K_M
Phi-4 14B21tok/sQ4_K_Moffload
Qwen 3.5 4B47tok/sQ8_035tok/sQ8_0
Ministral 3 8B22tok/sQ8_027tok/sQ4_K_M
Granite 4.2 8B21tok/sQ8_025tok/sQ4_K_M
Gemma 4 E4B26tok/sQ8_029tok/sQ5_K_M
LFM2.5 8B-A1B91tok/sQ8_088tok/sUD-Q5_K_M
Llama 3.1 8B29tok/sQ6_K25tok/sQ5_K_M
Qwen2.5 0.5B353tok/sQ8_0267tok/sQ8_0
Qwen3.5 0.8B240tok/sQ8_0181tok/sQ8_0
Qwen3.5 2B144tok/sQ5_K_M109tok/sQ5_K_M
LFM3 1.7B114tok/sQ8_086tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B105tok/sQ8_079tok/sQ8_0
MiniCPM5 2B74tok/sQ8_056tok/sQ8_0
LFM2.5 2.6B66tok/sQ8_050tok/sQ8_0
LFM2.5 VL 3B66tok/sQ8_050tok/sQ8_0
Spark X2.5 4B66tok/smlx-4bit50tok/smlx-4bit
Kimi VL A3B Thinking 250661tok/sQ4_K_Moffload
Mellum2.1 12B A2.5B Thinking61tok/sQ5_K_Moffload
granite vision 4.1 4b52tok/sQ8_039tok/sQ8_0
Ministral 3 3B Instruct 251249tok/sQ8_037tok/sQ8_0
granite 4.2 3b49tok/sQ8_037tok/sQ8_0
FrogNano 4B 260945tok/sQ8_034tok/sQ8_0
DeepSeek R1 Distill Qwen 7B26tok/sQ8_025tok/sQ6_K
GLM 4 9B 041426tok/smlx-5bitoffload
DeepSeek R1 Distill Llama 8B23tok/sQ8_025tok/sQ5_K_M
Ministral 3 8B Reasoning 251222tok/sQ8_027tok/sQ4_K_M
GLM 4.6V Flash22tok/sQ8_026tok/sQ4_K_M
DeepSeek R1 Distill Qwen 14B21tok/sQ4_K_Moffload
Ministral 3 14B Reasoning 251220tok/sQ5_K_Moffload
Qwen 3.8 27Boffloadoffload
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
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
gpt-oss 20Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
Gemma 3 27Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Kimi VL A3Boffloadoffload
LFM2.5 24B A2Boffloadoffload
GLM 4.1V 9B Thinkingoffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
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
Qwen 3.5 122B-A10Bwon'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
Mistral Small 4 119Bwon'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 GeForce RTX 3060 12GB or the NVIDIA GeForce RTX 4060?
Choose the NVIDIA GeForce RTX 3060 12GB to run bigger models. Choose the NVIDIA GeForce RTX 3060 12GB for speed. Choose the NVIDIA GeForce RTX 3060 12GB to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 3060 12GB or the NVIDIA GeForce RTX 4060?
At 8k context the NVIDIA GeForce RTX 3060 12GB runs 35 of the models we track fully in memory and the NVIDIA GeForce RTX 4060 26; only the NVIDIA GeForce RTX 3060 12GB holds Gemma 4 12B.
Which is faster for local AI, the NVIDIA GeForce RTX 3060 12GB or the NVIDIA GeForce RTX 4060?
On the models both run fully in memory, the NVIDIA GeForce RTX 3060 12GB is about 1.3× as fast as the NVIDIA GeForce RTX 4060 (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 3060 12GB and the NVIDIA GeForce RTX 4060?
In Canada the NVIDIA GeForce RTX 3060 12GB costs $530 at Amazon and the NVIDIA GeForce RTX 4060 $839 at Amazon: the NVIDIA GeForce RTX 3060 12GB is $309 cheaper.

More comparisons

More hardware for local AI