zanish-labs/gemma-4-e2b-q4km-gguf overview
Gemma 4 E2B — GGUF Q4 K M + mmproj Google's Gemma 4 E2B vision model, packaged for on device inference via llama.cpp. Includes both the base model and the mult…
Runs locally from ~531.5 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | zanish-labs/gemma-4-e2b-q4km-gguf |
|---|---|
| Author | zanish-labs |
| Pipeline | — |
| License | gemma |
| Base model | — |
| Last modified | 2026-07-10T11:04:28.000Z |
Model README
---
language:
- en
license: gemma
library_name: gguf
tags:
- vision
- multimodal
- gguf
- gemma
---
Gemma 4 E2B — GGUF (Q4_K_M + mmproj)
Google's Gemma 4 E2B vision model, packaged for on-device inference via llama.cpp. Includes both the base model and the multimodal projector.
Contents
| File | Description | Quantization |
|------|-------------|-------------|
| gemma-4-E2B-it-Q4_K_M.gguf | Base model (text + vision) | Q4_K_M |
| mmproj-gemma-4-E2B-it-Q8_0.gguf | Multimodal projector | Q8_0 |
Source
The base model is sourced from ggml-org/gemma-4-e2b-it-GGUF.
The mmproj file is sourced from ggml-org/gemma-4-e2b-it-GGUF with full attribution.
License
This model is subject to the Gemma Terms of Use. Copyright 2024 Google LLC.
Run zanish-labs/gemma-4-e2b-q4km-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models