Gemma 3 27B Instruct — VRAM, Speed & Local Setup

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 12 marca 2025

Model library → Gemma 3 → Gemma 3 27B Instruct

Google's most capable local model. Near-frontier performance at 27B scale. Requires 16GB VRAM, making it ideal for RTX 4080/4090 and Apple Silicon with 32GB+ unified memory.

Gemma 3 27B Instruct needs about 17 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

Parameters27 Billion
Context window128,000
ArchitectureDense
ProviderGoogle
LicenceGemma Terms
Specified atQ4_K_M
System RAM32 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_K8.9 GB18.0 GB~51 tok/s (est.)Fits comfortably
Q3_K_M11.5 GB20.6 GB~44 tok/s (est.)Fits comfortably
Q4_K_M16.3 GB25.4 GB~5 tok/s (est.)Offloads to system RAM (slow)
Q5_K_M19.1 GB28.3 GB~5 tok/s (est.)Offloads to system RAM (slow)
Q6_K22.1 GB31.3 GB~4 tok/s (est.)Offloads to system RAM (slow)
Q8_028.7 GB37.8 GB~3 tok/s (est.)Offloads to system RAM (slow)
F1654.0 GB63.1 GB—Won't fit

Want the memory numbers alone, at every quantization level and your own context length? Use the Gemma 3 27B Instruct VRAM calculator.

Buy This HardwareAMD Radeon RX 7900 XT 20GB — 20 GB VRAM · 315 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 27B Instruct is the AMD Radeon RX 7900 XT (20 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.
AMD Radeon RX 7900 XT 20GB
20 GB VRAM · 315 W board power
Ceny w 2026 są niestabilne — sprawdź aktualną ofertę.
Sprawdź cenę na Amazon

How to Run Gemma 3 27B Instruct

Install Ollama, then run:

ollama run gemma3:27b

Weights on Hugging Face: google/gemma-3-27b-it.

Best for: chat, reasoning, creative, coding.

Can I Run Gemma 3 27B Instruct on My GPU?

Other Gemma 3 Sizes

Gemma 3 27B Instruct — Frequently Asked Questions

How much VRAM does Gemma 3 27B Instruct need?
About 17 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 27B Instruct run on an RTX 4090 (24 GB)?
Yes. Gemma 3 27B Instruct needs about 17 GB at Q4_K_M, inside a 24 GB card, at an estimated 5 tokens/sec.
How do I run Gemma 3 27B Instruct locally?
Install Ollama and run `ollama run gemma3:27b`. 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