back to local model checker

Gemma 2 27B

Google · 27B · Dense

Google's largest Gemma 2 model

Gemma
Downloads

404.9K

Likes

560

Released

2024-06

Context

8K tokens

Use cases

chatreasoning

Your hardware

16 GB Reference Desktop

Quant
Q4_K_M
Memory
14.3 GB
Speed
~14 tok/s
Fit
Barely runs

Quantization options

What is quantization?
QuantBitsVRAMDiskQualityStatus
Q2_K29.1 GB8.3 GBlowDecent · ~22 t/s
Q3_K_M312.6 GB11.6 GBmoderateTight fit · ~16 t/s
Q4_K_M414.3 GB13.2 GBgoodBarely runs · ~14 t/s
Q5_K_M517.8 GB16.5 GBgoodBarely runs · ~6 t/s
Q6_K621.2 GB19.8 GBexcellentBarely runs · ~4 t/s
Q8_0828.2 GB26.4 GBexcellentBarely runs · ~2 t/s
F161655.8 GB52.8 GBlosslessToo heavy · ~1 t/s

About this model

Gemma 2 27B (Gemma 2 27b) is a 27B dense transformer from Google in the Gemma family, designed primarily for chat, reasoning workflows. Supports up to 8K context tokens; start at 4K–8K with Q8_0 KV cache on tight GPUs.

Hardware planning baselines start at 15.1 GB minimum memory and 25.1 GB recommended memory. At Q4_K_M, weights plus baseline runtime overhead use roughly 14.3 GB of RAM/VRAM and 13.2 GB of disk space. As a 27B dense checkpoint, every parameter participates in each token forward pass, meaning decoding speed scales linearly with GPU memory bandwidth and drops sharply if layers spill over PCIe into host DDR5 RAM.

Deploy Gemma 2 27B locally via Ollama (`gemma2:27b`), Ollama with Flash Attention enabled. Under Gemma Terms of Use, review official weight cards before commercial redistribution.

Highlights

  • Local Fit Baseline15.1 GB minimum and 25.1 GB recommended RAM/VRAM.
  • Primary QuantQ4_K_M targets 14.3 GB memory and 13.2 GB disk.
  • Context & Capabilities8K max context · Dense.

System requirements by device

Memory planning targets 15.1 GB minimum RAM/VRAM and 25.1 GB recommended memory. The baseline quant is Q4_K_M, estimated at 14.3 GB memory and 13.2 GB disk. Actual runtime usage shifts with context length, KV cache precision, and OS background overhead.

DeviceNotes
Mac (Apple silicon)Use unified memory headroom (~75% physical RAM max) as the primary fit signal. Start with Q4_K_M and close heavy browser tabs first.
Windows / Linux GPUKeep weights plus KV cache inside dedicated VRAM so Windows WDDM does not spill layers over PCIe into Shared GPU Memory.
Phones & Compact Edge BoardsNot practical on phones (15.1 GB min RAM exceeds Android LMK and iOS Jetsam limits). Pick a 2B–4B model on mobile.

Start with a short session and leave memory for the operating system. A file fitting on disk does not guarantee that it will load in memory.

Estimated memory by quantization

These are rough estimates, not tested minimum requirements. Check the actual file and runtime documentation; context, offloading and operating-system overhead can change the memory needed.

Quant TierEstimated memoryDisk SizeQuality
Q2_K9.1 GB8.3 GBlow
Q3_K_M12.6 GB11.6 GBmoderate
Q4_K_M14.3 GB13.2 GBgood
Q5_K_M17.8 GB16.5 GBgood
Q6_K21.2 GB19.8 GBexcellent
Q8_028.2 GB26.4 GBexcellent
F1655.8 GB52.8 GBlossless

How to run Gemma 2 27B on your device

Start with a short prompt and the smallest quant that still gives the quality you need. A clean first run is more useful than loading a larger file with no memory headroom.

Mac

Run Gemma 2 27B on Mac

  1. Install Ollama or LM Studio on macOS Apple Silicon.
  2. Pull Q4_K_M (14.3 GB) first and confirm it stays below ~75% of your Mac's unified memory.
  3. Enable Flash Attention and cap initial context at 8K until memory pressure stays below 25.1 GB.
  4. Consult the Mac guide for Activity Monitor tuning and Metal offload tips.
Device how-to guide
Windows

Run Gemma 2 27B on Windows

  1. Install LM Studio for Windows for visual VRAM inspection, or Ollama when you want a localhost API endpoint.
  2. Load Q4_K_M (~14.3 GB) and verify Dedicated GPU Memory stays within VRAM without spilling into Shared GPU Memory.
  3. Reserve at least 15.1 GB memory minimum and target 25.1 GB for comfortable context growth.
  4. Enable Q8_0 KV cache or drop one quant tier if generation slows down over PCIe.
Device how-to guide

Gemma 2 27B vs alternatives

ModelParamsContextMin RAMLicense
Gemma 2 27B27B8K15.1 GBGemma
Gemma 3 27B27B128K15.1 GBGemma
Gemma 4 26B-A4B IT27B (4B active)256K15.1 GBGemma
Gemma 4 26B-A4B27B (4B active)256K15.1 GBGemma
DiffusionGemma 26B-A4B IT26B (4B active)256K14.5 GBApache 2.0
Gemma 4 31B IT33B256K18.4 GBGemma

Use this table to choose the smallest nearby model that still matches the job. A related model with lower RAM can be the better local choice when the current page fits only at the edge of available memory.

Frequently asked questions

What is Gemma 2 27B?
Gemma 2 27B is a 27B dense transformer from Google, supporting up to 8K tokens with 15.1 GB minimum RAM and 25.1 GB recommended RAM.
What is the best way to run Gemma 2 27b locally?
Choose the smallest quant that matches the task, test one short prompt, then compare RAM, context, and nearby models before making Gemma 2 27B your default local model.
How much VRAM or RAM does Gemma 2 27B require?
At Q4_K_M, Gemma 2 27B occupies roughly 14.3 GB of active memory and 13.2 GB on disk. Add 2–6 GB of spare headroom for KV cache buffers, runtime scratch space, and OS apps (25.1 GB recommended).
What is the best way to run Gemma 2 27B locally?
Use `ollama run gemma2:27b` for a quick CLI/API setup, or load Q4_K_M in LM Studio or llama.cpp with Flash Attention enabled when you want explicit KV cache and layer control.
Can Gemma 2 27B run on Android or iPhone?
Gemma 2 27B requires 15.1 GB minimum memory, placing it outside practical 8 GB smartphone limits. Run it on a 16 GB+ Mac or desktop GPU instead, and pick a 2B–4B checkpoint for phones.
How does Gemma 2 27B compare to Gemma 3 27B?
Gemma 3 27B (27B, 15.1 GB min RAM) sits closest in size. Compare active parameters, context ceiling (8K vs 128K), and license terms (Gemma) before switching.