Gemma 3 12B Instruct — VRAM, Speed & Local Setup

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

作者： Jakub Rusinowski · 最后更新： 2025年3月12日

Model library → Gemma 3 → Gemma 3 12B Instruct

The sweet spot of the Gemma 3 family. Rivals Llama 3.3 70B in many tasks while fitting comfortably in 8GB VRAM. Exceptional for creative writing and coding.

Gemma 3 12B Instruct needs about 8 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters	12 Billion
Context window	128,000
Architecture	Dense
Provider	Google
Licence	Gemma Terms
Specified at	Q4_K_M
System RAM	16 GB
Record updated	2025-03-12

Licence

Gemma Terms — commercial use permitted. Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB), at 8K context. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

Quant	Weights	VRAM needed	Est. speed	Fit on 24 GB
Q2_K	3.9 GB	7.8 GB	~105 tok/s (est.)	Fits comfortably
Q3_K_M	5.1 GB	9.0 GB	~90 tok/s (est.)	Fits comfortably
Q4_K_M	7.2 GB	11.1 GB	~72 tok/s (est.)	Fits comfortably
Q5_K_M	8.5 GB	12.4 GB	~64 tok/s (est.)	Fits comfortably
Q6_K	9.8 GB	13.7 GB	~58 tok/s (est.)	Fits comfortably
Q8_0	12.8 GB	16.6 GB	~47 tok/s (est.)	Fits comfortably
F16	24.0 GB	27.9 GB	~4 tok/s (est.)	Offloads to system RAM (slow)

Want the memory numbers alone, at every quantization level and your own context length? Use the Gemma 3 12B Instruct VRAM calculator.

Buy This HardwareIntel Arc B570 10GB — 10 GB VRAM · 150 W board power Deploy in the Cloud NowRTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Recommended GPU

The cheapest catalogued GPU that runs Gemma 3 12B Instruct is the Intel Arc B570 (10 GB).

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买，LLM Configurator 可能会获得佣金，而你无需支付任何额外费用。作为亚马逊联盟成员（Amazon Associate），LLM Configurator 会从符合条件的购买中获得收益。

Intel Arc B570 10GB

10 GB VRAM · 150 W board power

2026年价格波动较大——请以当前商品页价格为准。

在亚马逊查看价格

How to Run Gemma 3 12B Instruct

Install Ollama, then run:

ollama run gemma3:12b

Weights on Hugging Face: google/gemma-3-12b-it.

Best for: chat, creative, coding, balanced.

Can I Run Gemma 3 12B Instruct on My GPU?

Other Gemma 3 Sizes

Gemma 3 1B Instruct — about 1 GB VRAM at Q4_K_M
Gemma 3 4B Instruct — about 3 GB VRAM at Q4_K_M
Gemma 3 27B Instruct — about 17 GB VRAM at Q4_K_M

Gemma 3 12B Instruct — Frequently Asked Questions

How much VRAM does Gemma 3 12B Instruct need?

About 8 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does Gemma 3 12B Instruct run on an RTX 4090 (24 GB)?

Yes. Gemma 3 12B Instruct needs about 8 GB at Q4_K_M, inside a 24 GB card, at an estimated 72 tokens/sec.

How do I run Gemma 3 12B Instruct locally?

Install Ollama and run `ollama run gemma3:12b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does Gemma 3 come in?

Gemma 3 1B Instruct (1 GB), Gemma 3 4B Instruct (3 GB), Gemma 3 12B Instruct (8 GB), Gemma 3 27B Instruct (17 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All Gemma 3 models | VRAM calculator | Build a PC for this model | Check your own hardware