What can NVIDIA GeForce RTX 3060 12GB run locally?

44 models fit comfortably on NVIDIA GeForce RTX 3060 12GB with 32 GB system RAM. 166 more run with tradeoffs. Top pick: Hermes 3 Llama 3.2 3B.

What's the recommended runner for this hardware?

llama.cpp / Ollama (CUDA). This is the runner that gives best tokens-per-second on NVIDIA GeForce RTX 3060 12GB based on windows support and the GPU backend.

What can NVIDIA GeForce RTX 3060 12GB run for creative?

Build: NVIDIA GeForce RTX 3060 12GB + — + 32 GB RAM (windows)

Memory: 12 GB VRAM + 32 GB system RAM

Runner: llama.cpp / Ollama (CUDA)

Any Chat Coding Agents Reasoning Vision Long context Creative

Runs comfortably
44 models

Ranked by fit for creative use case + predicted speed. Click a row for VRAM breakdown.

#1Hermes 3 Llama 3.2 3B

hermes

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 6.8 GBTTFT: noticeable

129

tok/s

Estimated

Weights

1.80 GB

KV cache

1.50 GB

Activations

0.10 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)

Model details →

#2Dolphin 3.0 Llama 3.2 3B

dolphin

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 5.2 GBHeadroom: 6.8 GBTTFT: noticeable

129

tok/s

Estimated

Weights

1.80 GB

KV cache

1.50 GB

Activations

0.10 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)

Model details →

#3Gemma 2 2B Instruct

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 4.0 GBHeadroom: 8.0 GBTTFT: fast

194

tok/s

Estimated

Weights

1.10 GB

KV cache

1.00 GB

Activations

0.06 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~403 ms (fast)

Model details →

#4Gemma 4 E2B (Effective 2B)

gemma

Commercial OK

Quant: Q8_0Context: 8,192VRAM: 5.1 GBHeadroom: 6.9 GBTTFT: fast

ollama run gemma4:e2b

110

tok/s

Estimated

Weights

2.20 GB

KV cache

1.00 GB

Activations

0.12 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~403 ms (fast)

Model details →

#5Qwen 3 1.7B

1.7B

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 3.6 GBHeadroom: 8.4 GBTTFT: fast

228

tok/s

Estimated

Weights

0.90 GB

KV cache

0.85 GB

Activations

0.05 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~343 ms (fast)

Model details →

#6Kumru 2B

2.4B

mistral

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 4.6 GBHeadroom: 7.4 GBTTFT: fast

ollama run alibayram/kumru:latest

161

tok/s

Estimated

Weights

1.50 GB

KV cache

1.20 GB

Activations

0.08 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~484 ms (fast)

Model details →

#7Qwen 3.5 2B Turkish SFT

qwen

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 4.0 GBHeadroom: 8.0 GBTTFT: fast

194

tok/s

Estimated

Weights

1.10 GB

KV cache

1.00 GB

Activations

0.06 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~403 ms (fast)

Model details →

#8Kanarya 2B

other

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 3.2 GBHeadroom: 8.8 GBTTFT: fast

194

tok/s

Estimated

Weights

1.10 GB

KV cache

0.25 GB

Activations

0.06 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~403 ms (fast)

Model details →

#9EXAONE 3.5 2.4B Instruct

2.4B

exaone

Quant: Q4_K_MContext: 8,192VRAM: 4.4 GBHeadroom: 7.6 GBTTFT: fast

161

tok/s

Estimated

Weights

1.30 GB

KV cache

1.20 GB

Activations

0.07 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~484 ms (fast)

Model details →

#10Granite 3.1 2B Instruct

granite

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 4.0 GBHeadroom: 8.0 GBTTFT: fast

194

tok/s

Estimated

Weights

1.10 GB

KV cache

1.00 GB

Activations

0.06 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~403 ms (fast)

Model details →

#11Falcon 3 3B Instruct

falcon

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 5.1 GBHeadroom: 6.9 GBTTFT: noticeable

129

tok/s

Estimated

Weights

1.70 GB

KV cache

1.50 GB

Activations

0.09 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)

Model details →

#12Salamandra 2B

2.25B

llama

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 4.2 GBHeadroom: 7.8 GBTTFT: fast

172

tok/s

Estimated

Weights

1.20 GB

KV cache

1.13 GB

Activations

0.07 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~454 ms (fast)

Model details →

Runs with tradeoffs
166 models

Tight VRAM, partial CPU offload, or context-limited.

Hermes 3 Llama 3.1 8B

hermes

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 11.0 GBHeadroom: 1.0 GBTTFT: noticeable

• Tight VRAM fit — only 1.0 GB headroom left for context growth

ollama run hermes3:8b

tok/s

Estimated

Weights

4.90 GB

KV cache

4.00 GB

Activations

0.25 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1613 ms (noticeable)

Model details →

Gemma 2 9B Instruct

gemma

Commercial OK

Quant: Q4_K_MContext: 2,048VRAM: 9.0 GBHeadroom: 3.0 GBTTFT: noticeable

• Tight VRAM fit — only 3.0 GB headroom left for context growth

ollama run gemma2:9b

tok/s

Estimated

Weights

5.80 GB

KV cache

1.13 GB

Activations

0.29 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1814 ms (noticeable)

Model details →

Dolphin 3.0 8B

dolphin

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 11.1 GBHeadroom: 0.9 GBTTFT: noticeable

• Tight VRAM fit — only 0.9 GB headroom left for context growth

ollama run dolphin3:8b

tok/s

Estimated

Weights

5.00 GB

KV cache

4.00 GB

Activations

0.26 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1613 ms (noticeable)

Model details →

DeepSeek V2 Lite Chat

15.7B

deepseek

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 18.7 GBHeadroom: 12.5 GBTTFT: fast

• Partial CPU offload: ~36% of layers run on CPU

161

tok/s

Estimated

Weights

8.60 GB

KV cache

7.85 GB

Activations

0.44 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~484 ms (fast)

Model details →

Granite 3 MoE (3B active)

16B

granite

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 19.8 GBHeadroom: 11.4 GBTTFT: noticeable

• Partial CPU offload: ~39% of layers run on CPU

129

tok/s

Estimated

Weights

9.50 GB

KV cache

8.00 GB

Activations

0.48 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~605 ms (noticeable)

Model details →

DeepSeek MoE 16B Base

16B

deepseek

Commercial OK

Quant: Q4_K_MContext: 4,096VRAM: 15.8 GBHeadroom: 15.4 GBTTFT: fast

• Partial CPU offload: ~24% of layers run on CPU

161

tok/s

Estimated

Weights

9.50 GB

KV cache

4.00 GB

Activations

0.48 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~484 ms (fast)

Model details →

DeepSeek V3 Lite (16B MoE)

16B

deepseek

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 19.8 GBHeadroom: 11.4 GBTTFT: fast

• Partial CPU offload: ~39% of layers run on CPU

161

tok/s

Estimated

Weights

9.50 GB

KV cache

8.00 GB

Activations

0.48 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~484 ms (fast)

Model details →

CodeGemma 7B

gemma

Commercial OK

Quant: Q4_K_MContext: 8,192VRAM: 9.7 GBHeadroom: 2.3 GBTTFT: noticeable

• Tight VRAM fit — only 2.3 GB headroom left for context growth

ollama run codegemma:7b

tok/s

Estimated

Weights

4.20 GB

KV cache

3.50 GB

Activations

0.22 GB

Runtime

1.80 GB

Time to first token (prefill, 512-token prompt): ~1411 ms (noticeable)

Model details →

What if you upgraded?

Hypothetical scenarios. We re-ran the compatibility engine for each.

+32 GB system RAM

~$80–150

Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.

Unlocks: 23 new comfortable, 174 new tradeoff

• Qwen 3 0.6B
• Gemma 3 270M
• SmolLM2 135M Instruct
• TinyLlama 1.1B Chat v1.0

Shop this upgrade↗

Upgrade to NVIDIA GeForce RTX 4070 Ti Super

~$829

16 GB VRAM (vs your 12 GB) plus a bandwidth jump from ~360 GB/s to ~672 GB/s.

Unlocks: 98 new comfortable

• Qwen 3 0.6B
• Llama 3.1 8B Instruct
• Qwen 3 8B
• Gemma 3 270M

Shop this upgrade↗

Add a second NVIDIA GeForce RTX 3060 12GB

~$249

Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.

Unlocks: 140 new comfortable

• Qwen 3 0.6B
• Llama 3.1 8B Instruct
• Qwen 3 8B
• Gemma 4 12B

Shop this upgrade↗

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

Won't run
top 5 popular models

Need more memory than you have. Shown for orientation.

DeepSeek V4 Pro (1.6T MoE)

1600B

deepseek

Commercial OK