Skip to main content
12 GB VRAM 23 models checked 200 guides

RTX 3060 12GB for Local LLMs: What It Runs, What It Costs, Every Guide

The RTX 3060 12GB's 12 GB holds models up to about Phi-4 14B entirely in VRAM: its 9.1 GB Q4_K_M file leaves 2.9 GB for context (per the SpecPicks Will-It-Run matrix). New, it is $400 this week, $33.33 per GB of VRAM, per the Amazon listings SpecPicks tracks (price may vary).

By SpecPicks Editorial — AI Rigs Team

What fits in 12 GB

Each row is the model’s real Q4_K_M GGUF file size against the card’s 12 GB, with the median of published, source-linked generation-speed runs that pass a memory-bandwidth sanity check. Open a row for the sources behind it.

ModelQ4 fileVerdictMedian speed
Llama 3.2 1B 0.8 GB Q4_K_M Runs 185 tok/s 2 cited runs
Llama 3.2 3B 2 GB Q4_K_M Runs 126 tok/s 2 cited runs
Mistral 7B 4.4 GB Q4_K_M Runs no cited run
Qwen2.5 7B 4.7 GB Q4_K_M Runs no cited run
Llama 3.1 8B 4.9 GB Q4_K_M Runs 52.2 tok/s 5 cited runs
DeepSeek-R1-Distill-Llama 8B 4.9 GB Q4_K_M Runs no cited run
Qwen3 8B 5 GB Q4_K_M Runs 48.6 tok/s 4 cited runs
Gemma 2 9B 5.8 GB Q4_K_M Runs no cited run
Gemma 3 12B 7.3 GB Q4_K_M Runs no cited run
Qwen2.5 14B 9 GB Q4_K_M Runs 26.5 tok/s 2 cited runs
DeepSeek-R1-Distill-Qwen 14B 9 GB Q4_K_M Runs 29.4 tok/s 1 cited run
Qwen3 14B 9 GB Q4_K_M Runs 28.1 tok/s 2 cited runs
Phi-4 14B 9.1 GB Q4_K_M Runs no cited run
gpt-oss-20b 12.1 GB MXFP4 Offload no cited run
Gemma 3 27B 16.6 GB Q4_K_M Offload no cited run
Gemma 2 27B 16.7 GB Q4_K_M Offload no cited run
Qwen3 30B-A3B 18.6 GB Q4_K_M Offload no cited run
Qwen3 32B 19.8 GB Q4_K_M Offload no cited run
Qwen2.5 32B 19.9 GB Q4_K_M Offload no cited run
DeepSeek-R1-Distill-Qwen 32B 19.9 GB Q4_K_M Offload no cited run
Llama 3.1 70B 42.5 GB Q4_K_M Offload no cited run
Llama 3.3 70B 42.5 GB Q4_K_M Offload no cited run
DeepSeek-R1-Distill-Llama 70B 42.5 GB Q4_K_M Offload no cited run

What it costs this week

  • New (Amazon): $400 · $33.33 per GB of VRAM
  • Used (eBay median, 7 days): withheld — 1 listing seen, fewer than 8

View Current Price →DetailsUsed on eBay

*Tracked snapshot read 2026-10-06, not a live quote: price may vary. Its row in this week’s LLM GPU Price Index →

Every RTX 3060 12GB guide, by question

200 SpecPicks guides cover this card. They are grouped by the question they answer, most-read first.

Compared with other cards and machines 50 guides

38 more

Backends, drivers and runtimes 15 guides

3 more

Front-ends, agents and tools 36 guides

24 more

Specific models 39 guides

27 more

Gaming 21 guides

9 more

Builds, buying and value 10 guides

Everything else 28 guides

16 more

Where to go next

As an Amazon Associate, SpecPicks earns from qualifying purchases.

This page is editorial synthesis based on publicly available information. No independent first-party benchmarking is reported.