LocalClaw/LLM/Gemma 4 E2B
Open-weight local LLM

Gemma 4 E2B

Catalogue summary: Gemma 4 compact multimodal model for on-device usage. Supports text, image, audio, and video understanding with 256K context. Apache 2.0.

Repository editorial metadata; verify comparative claims in the linked upstream material.

6 GB catalogue minimum6 GB RAMQ5_K_MVision tasks
Choose an app

Pick the app you already use. No terminal and no command to copy.

Compare models
Open in LM StudioOpens the app on this model's download screenOpen in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens the model filesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
E2B
Minimum RAM
6 GB
Model size
3.4 GB
Quantization
Q5_K_M

Can Gemma 4 E2B run locally?

Gemma 4 E2B has a catalogue minimum of 6 GB RAM with Q5_K_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use gemma-4-e2b-it as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

Public GGUF repository (verified 2026-09-07): unsloth/gemma-4-E2B-it-GGUFUpstream releasePaper or model cardLicence text
chatvisionspeededgemultimodalgeneral

Install path

01
Check RAM fitMinimum 6 GB RAM. Start with the Q5_K_M quant.
02
Load the modelSearch gemma-4-e2b-it in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: gemma
  • Parameters: E2B
  • Recommended quantization: Q5_K_M
  • Catalogue minimum RAM: 6 GB
  • Catalogue model size: 3.4 GB
  • Tags: chat, vision, speed, edge, multimodal, general

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • vision
  • speed
  • edge
  • multimodal
  • general

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
9
quality
6
coding
5
reasoning
6

Technical notes

Developer
Google DeepMind
License
Apache 2.0
Context window
262,144 tokens
Architecture
Gemma 4 multimodal Transformer (edge tier)

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Entry laptop fitMacBook Air 8GBMore headroomMac mini M4 16GBAll compatible picks8GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

Gemma 4 E4B E4BGemma 4 12B 12BGemma 3 (4B) 4BGemma 3 (12B) 12BGemma 4 26B A4B 26B (A4B active)DiffusionGemma 26B-A4B Instruct 26B (4B active, diffusion MoE)Gemma 3 (27B) 27BGemma 4 31B 31B

Where to go next