Gemma 3 1B Instruct — VRAM, Speed & Local Setup

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 12 marca 2025

Model library → Gemma 3 → Gemma 3 1B Instruct

Google's smallest Gemma 3 model — fits on any phone or microcontroller. Surprisingly capable for on-device AI tasks. The best 1B model from a major lab for offline mobile use.

Gemma 3 1B Instruct needs about 1 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

Parameters1 Billion
Context window32,000
ArchitectureDense
ProviderGoogle
LicenceGemma Terms
Specified atQ4_K_M
System RAM2 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_K0.3 GB1.7 GB~325 tok/s (est.)Fits comfortably
Q3_K_M0.4 GB1.8 GB~312 tok/s (est.)Fits comfortably
Q4_K_M0.6 GB2.0 GB~290 tok/s (est.)Fits comfortably
Q5_K_M0.7 GB2.1 GB~279 tok/s (est.)Fits comfortably
Q6_K0.8 GB2.2 GB~268 tok/s (est.)Fits comfortably
Q8_01.1 GB2.5 GB~247 tok/s (est.)Fits comfortably
F162.0 GB3.4 GB~189 tok/s (est.)Fits comfortably

Want the memory numbers alone, at every quantization level and your own context length? Use the Gemma 3 1B 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 1B Instruct is the Intel Arc B570 (10 GB).

Ujawnienie afiliacyjne: Niektóre odnośniki na tej stronie to linki afiliacyjne — jeśli dokonasz zakupu za ich pośrednictwem, LLM Configurator może otrzymać prowizję bez dodatkowych kosztów dla Ciebie. Jako uczestnik programu Amazon Associates, LLM Configurator zarabia na kwalifikujących się zakupach.
Intel Arc B570 10GB
10 GB VRAM · 150 W board power
Ceny w 2026 są niestabilne — sprawdź aktualną ofertę.
Sprawdź cenę na Amazon

How to Run Gemma 3 1B Instruct

Install Ollama, then run:

ollama run gemma3:1b

Weights on Hugging Face: google/gemma-3-1b-it.

Best for: mobile, edge devices, offline chat, low vram.

Can I Run Gemma 3 1B Instruct on My GPU?

Other Gemma 3 Sizes

Gemma 3 1B Instruct — Frequently Asked Questions

How much VRAM does Gemma 3 1B Instruct need?
About 1 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 1B Instruct run on an RTX 4090 (24 GB)?
Yes. Gemma 3 1B Instruct needs about 1 GB at Q4_K_M, inside a 24 GB card, at an estimated 290 tokens/sec.
How do I run Gemma 3 1B Instruct locally?
Install Ollama and run `ollama run gemma3:1b`. 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 | Check your own hardware