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

Written by Jakub Rusinowski · Last updated March 12, 2025

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

Parameters12 Billion
Context window128,000
ArchitectureDense
ProviderGoogle
LicenceGemma Terms
Specified atQ4_K_M
System RAM16 GB
Record updated2025-03-12

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.

QuantWeightsVRAM neededEst. speedFit on 24 GB
Q2_K3.9 GB7.8 GB~105 tok/s (est.)Fits comfortably
Q3_K_M5.1 GB9.0 GB~90 tok/s (est.)Fits comfortably
Q4_K_M7.2 GB11.1 GB~72 tok/s (est.)Fits comfortably
Q5_K_M8.5 GB12.4 GB~64 tok/s (est.)Fits comfortably
Q6_K9.8 GB13.7 GB~58 tok/s (est.)Fits comfortably
Q8_012.8 GB16.6 GB~47 tok/s (est.)Fits comfortably
F1624.0 GB27.9 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 powerDeploy 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).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
Intel Arc B570 10GB
10 GB VRAM · 150 W board power
2026 prices are volatile — check the current listing.
Check price on Amazon

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 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