Device profile · Windows

Best local LLMs for Nvidia GeForce RTX 3060 Ti (8GB)

Nvidia GeForce RTX 3060 Ti (8GB) has ~7 GB usable for model weights and runs 54 of 149 popular models. Best tool: LM Studio.

42 run well 12 tight fit 95 too heavy

Usable memory: ~7 GB
Models run: 54
Too large: 95
Top pick: 4B

Top pick Q4_K_M

Gemma 3 4B Yes

Runs at Q4_K_M using ~3.8 GB of ~7 GB usable. You have room for Q8_0 for higher quality.

Runs on Nvidia GeForce RTX 3060 Ti (8GB)

Compatible models 54 total

Too large for this device

Kimi K3 DeepSeek-V4-Pro Kimi K2 Instruct Kimi K2.6 Kimi K2.7 Code GLM-5.2 DeepSeek R1 DeepSeek V3 DeepSeek-R1-0528 Nemotron 3 Ultra 550B-A55B Qwen3-Coder 480B-A35B Instruct MiniMax-M1-80k MiniMax M3 Llama 4 Maverick GLM-4.6 GLM-5.3-Flash DeepSeek-V4-Flash Qwen3 235B A22B dots.llm1 Devstral 2 123B Nemotron 3 Super 120B-A12B Laguna S 2.1 gpt-oss 120B Command A Llama 4 Scout GLM-4.5-Air Sarvam-105B Hunyuan-A13B-Instruct Qwen2.5 72B Llama 3.3 70B Llama-3.3-Nemotron-Super-49B-v1 Mixtral 8x7B Seed-OSS 36B Instruct Qwen3.6 35B-A3B Command R 35B Ornith 1.0 35B Ornith 1.5 35B-A3B Qwen-AgentWorld 35B-A3B Yi 1.5 34B Falcon-H1-34B-Instruct Laguna XS 2.1 Gemma 4 31B Qwen2.5 32B Qwen3 32B DeepSeek-R1-Distill-Qwen 32B Qwen2.5 Coder 32B Granite 4.0 H Small GLM-4-32B-0414 EXAONE 4.0 32B OLMo 2 32B Instruct Granite 4.0 H Small Olmo 3.1 32B Instruct Qwen3 30B-A3B Qwen3-Coder 30B-A3B North Mini Code 1.0 Sarvam-30B Nemotron 3 Nano 30B-A3B Nemotron Cascade 2 30B-A3B GLM-4.7-Flash Muse Glimmer 30B Nemotron 3.5 Lightning 30B-A3B Granite 4.1 30B Qwen3.6 27B Gemma 2 27B Gemma 3 27B Qwen3.8 27B Gemma 4 26B-A4B Mistral Small 3 24B Sarvam-M 24B Mistral Small 3.1 24B Magistral Small Devstral Small LFM2 24B-A2B Devstral Small 2 24B gpt-oss 20B ERNIE 4.5 21B-A3B DeepSeek-V2-Lite Phi-4 14B Qwen2.5 14B Qwen3 14B DeepSeek-R1-Distill-Qwen 14B Qwen2.5 Coder 14B Phi-4-reasoning Ministral 3 14B Mistral Nemo 12B Gemma 3 12B Gemma 4 12B Llama 3.2 Vision 11B Falcon3 10B Gemma 2 9B GLM-4 9B GLM-4-9B-0414 Nemotron Nano 9B v2 Ornith 1.0 9B Qwen2.5-VL 7B

Best way to run models on Windows

Runtime guide Windows

Beginner: LM Studio, Best GUI on Windows, auto-detects CUDA/Vulkan backends.

Power user: Ollama (CUDA), Scriptable server; CUDA path is fastest on NVIDIA.

AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.

Full Windows tool guide →

FAQ

What is the best local LLM for Nvidia GeForce RTX 3060 Ti (8GB)?

Gemma 3 4B is the strongest model that runs comfortably, using ~3.8 GB at Q4_K_M of the ~7 GB usable on Nvidia GeForce RTX 3060 Ti (8GB).

How much of Nvidia GeForce RTX 3060 Ti (8GB)'s memory can I use for a model?

About 7 GB. On a discrete GPU, leave ~1 GB of VRAM for the driver and display.

Which tool should I use on Windows?

LM Studio (Best GUI on Windows, auto-detects CUDA/Vulkan backends.) or Ollama (CUDA) for speed. AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.

Compare nearby devices

Hardware with a similar usable pool, and how many of the 149 tracked models each runs next to Nvidia GeForce RTX 3060 Ti (8GB)'s 54.

Apple M2 (16GB)

~10.5 GB usable · runs 68 of 149

+14

Apple M4 (16GB)

~10.5 GB usable · runs 68 of 149

+14

Nvidia GeForce GTX 1070 (8GB)

~7 GB usable · runs 54 of 149

Apple M1 (8GB)

~5.5 GB usable · runs 38 of 149

-16

8GB RAM Laptop (CPU/iGPU only)

~5 GB usable · runs 38 of 149

-16

Nvidia GeForce RTX 2060 (6GB)

~5 GB usable · runs 38 of 149

-16

Sources

Memory figures are estimates. See methodology.