Shadow Studio mirror — Gemma 4 E2B IT (GGUF)

Unmodified GGUF copies of Gemma 4 E2B instruction-tuned weights,

mirrored as the stable download source for the

Shadow Studio local AI workspace

(Fast tier — smallest/lowest-latency chat model).

vision input (~0.9 GB)

Files are byte-identical re-hosts of the quantizations published by

bartowski (thanks!). No further

modification was made. Shadow Studio verifies each download against a

pinned SHA-256.

License

Gemma is provided under and subject to the Gemma Terms of Use found

at https://ai.google.dev/gemma/terms. Use of these weights is also

subject to Google's Prohibited Use Policy:

https://ai.google.dev/gemma/prohibited_use_policy

By downloading these files you agree to those terms. This repository is

deliberately not gated so that Shadow Studio's built-in downloader

(which carries no auth token) can fetch models directly; the app surfaces

the Gemma Terms notice in its Model Manager before download.

Question 2

What license applies to latentdivergence/shadow-gemma-4-E2B-it-GGUF?

Accepted Answer

License: gemma. Verify terms on Hugging Face before commercial use.

Question 3

How do I run latentdivergence/shadow-gemma-4-E2B-it-GGUF locally?

Accepted Answer

Download a GGUF file from this page and load it in guIDE or llama.cpp. Pipeline task: text-generation.

Question 4

How much VRAM or disk space does latentdivergence/shadow-gemma-4-E2B-it-GGUF need?

Accepted Answer

Runs locally from ~941.1 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

File	Type	Quantization	Size	Link
google_gemma-4-E2B-it-Q4_K_M.gguf	GGUF	Q4_K_M	3.22 GB	Download
mmproj-google_gemma-4-E2B-it-bf16.gguf	GGUF	BF16	941.1 MB	Download

Model ID	latentdivergence/shadow-gemma-4-E2B-it-GGUF
Author	latentdivergence
Pipeline	—
License	gemma
Base model	google/gemma-4-E2B-it
Last modified	2026-07-17T10:07:01.000Z