Google4B~3 GB VRAM at Q4_K_M

Gemma 3 4B Instruct — VRAM, speed & local setup

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

Written by Jakub Rusinowski · Last updated March 12, 2025

Outperforms Llama 3.1 8B on most benchmarks while requiring half the VRAM. The best small model for budget hardware. Runs on any GPU with 4GB+ VRAM.

Gemma 3 4B Instruct needs about 3 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.

Logic82

Creative80

Coding78

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.

Quant	VRAM	Speed (est.)	Fit
Q2_K 2.63 bpw	2.5 GB	~231 tok/s	Fits
Q3_K_M 3.41 bpw	2.9 GB	~206 tok/s	Fits
Q4_K_M 4.83 bpw	3.6 GB	~173 tok/s	Fits
Q5_K_M 5.67 bpw	4 GB	~158 tok/s	Fits
Q6_K 6.56 bpw	4.4 GB	~144 tok/s	Fits
Q8_0 8.50 bpw	5.4 GB	~122 tok/s	Fits
F16 16.00 bpw	9.2 GB	~76 tok/s	Fits

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Gemma 3 4B Instruct VRAM calculator →

Get Gemma 3 4B Instruct running

The cheapest catalogued GPU that runs Gemma 3 4B Instruct is the Intel Arc B570 (10 GB).

Buy this hardware Intel Arc B570 10GB — 10 GB VRAM · 150 W board power Deploy in the cloud now RTX 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.

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 4B Instruct

Install Ollama, then run:

$ollama run gemma3:4b

Weights on Hugging Face: google/gemma-3-4b-it ↗

Specifications

Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.

Parameters: 4 Billion
Context window: 128,000
Architecture: Dense
Provider: Google
Licence: Gemma Terms
Practical deployment: Edge device (phone, SBC)
Specified at: Q4_K_M
System RAM: 8 GB
Record updated: 2025-03-12

LicenceGemma TermsCommercial use permitted

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

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best forchatedge devicesbudget hardwaremobile

Can I run Gemma 3 4B Instruct on my GPU?

Other Gemma 3 sizes

Gemma 3 4B Instruct — frequently asked questions

How much VRAM does Gemma 3 4B Instruct need?

About 3 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 4B Instruct run on an RTX 4090 (24 GB)?

Yes. Gemma 3 4B Instruct needs about 3 GB at Q4_K_M, inside a 24 GB card, at an estimated 173 tokens/sec.

How do I run Gemma 3 4B Instruct locally?

Install Ollama and run `ollama run gemma3:4b`. 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.