GE

gemma-4-E2B-it

GemmaGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters4.95B
Context—
Layers—
Architecturegemma4e2b
Smallest quant1.6 GB
Quick answer

gemma-4-E2B-it needs about 3.6 GB of memory at Q4_K (a 2.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.6 GB (Q2_K) to 9.9 GB.

Gemma‑4‑E2B‑it GGUF model for text and audio tasks

Gemma‑4‑E2B‑it is a 4.95B‑parameter instruction‑tuned LLM with an audio encoder. It supports text generation, coding, and multimodal reasoning. The GGUF format enables local inference with llama.cpp.

Good at

  • Text generation
  • Audio‑to‑text conversion
  • Reasoning tasks

Limits

  • No vision support
  • Requires 8 k context for estimates
  • Apache‑2.0 license

Best for

  • Local inference on laptops
  • ASR pipelines
  • Multimodal research

Who it’s for. Developers and researchers who need a lightweight, instruction‑tuned Gemma model with audio capabilities for on‑device or edge deployment. The model is suitable for building ASR or multimodal applications without GPU requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.6 GB 2.3 GB
Fits Get file →
Q4_K2.8 GB 3.6 GB
Fits Get file →
Q8_05.3 GB 6.4 GB
Fits Get file →
—9.9 GB 11.6 GB
Too big Get file →

For 8 GB VRAM use Q4_K (2.79 GB file, ~3.6 GB RAM). For 4 GB VRAM use Q2_K (1.63 GB file, ~2.3 GB RAM). The Q8_0 variant (5.27 GB file, ~6.4 GB RAM) requires more memory but offers higher precision.

What GPU do you need for gemma-4-E2B-it?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q4_K (2.8 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K (2.8 GB file, about 3.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.3 GB file, about 6.4 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (9.9 GB file, about 11.6 GB in use).

Which gemma-4-E2B-it quant should you choose?

Q4_K (2.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K at 1.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4e2b
Parameters4.95B

Source

Quantized bycstr
FamilyGemma
Licenseapache-2.0
Downloads (HF)830
Last updated2026-08-02

Frequently asked questions about gemma-4-E2B-it

How much VRAM does gemma-4-E2B-it need?

About 3.6 GB at Q4_K with an 8K context window. That is the 2.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run gemma-4-E2B-it on an 8 GB GPU?

Yes, with Q8_0: the 5.3 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gemma-4-E2B-it GGUF?

It depends on the quant: Q2_K is 1.6 GB, Q4_K is 2.8 GB, Q8_0 is 5.3 GB, file is 9.9 GB.

Where can I download gemma-4-E2B-it GGUF?

The files are on Hugging Face in the cstr/gemma4-e2b-it-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does gemma-4-E2B-it use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Gemma‑4‑E2B‑it on 8 GB VRAM?

Yes, the Q4_K quantized file is 2.79 GB and requires about 3.6 GB of RAM at 8 k context.

Does this model support image input?

No, the GGUF variant includes only text and audio paths; vision support is omitted.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of gemma-4-E2B-it

Similar models

Browse all →

More from cstr

All by cstr →

More Gemma models

All Gemma →

Other small models

All small models →