Instructions to use sunsethunter86/gemma-lite-e2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use sunsethunter86/gemma-lite-e2b with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sunsethunter86/gemma-lite-e2b
# Run inference directly in the terminal:
llama cli -hf sunsethunter86/gemma-lite-e2b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sunsethunter86/gemma-lite-e2b
# Run inference directly in the terminal:
llama cli -hf sunsethunter86/gemma-lite-e2b

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf sunsethunter86/gemma-lite-e2b
# Run inference directly in the terminal:
./llama-cli -hf sunsethunter86/gemma-lite-e2b

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf sunsethunter86/gemma-lite-e2b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sunsethunter86/gemma-lite-e2b

Use Docker

docker model run hf.co/sunsethunter86/gemma-lite-e2b

LM Studio
Jan
Ollama
How to use sunsethunter86/gemma-lite-e2b with Ollama:
```
ollama run hf.co/sunsethunter86/gemma-lite-e2b
```

Unsloth Studio

How to use sunsethunter86/gemma-lite-e2b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for sunsethunter86/gemma-lite-e2b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for sunsethunter86/gemma-lite-e2b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sunsethunter86/gemma-lite-e2b to start chatting

How to use sunsethunter86/gemma-lite-e2b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sunsethunter86/gemma-lite-e2b

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "sunsethunter86/gemma-lite-e2b"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use sunsethunter86/gemma-lite-e2b with Docker Model Runner:
```
docker model run hf.co/sunsethunter86/gemma-lite-e2b
```

Lemonade

How to use sunsethunter86/gemma-lite-e2b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sunsethunter86/gemma-lite-e2b

Run and chat with the model

lemonade run user.gemma-lite-e2b-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use sunsethunter86/gemma-lite-e2b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sunsethunter86/gemma-lite-e2b

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default sunsethunter86/gemma-lite-e2b

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use sunsethunter86/gemma-lite-e2b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf sunsethunter86/gemma-lite-e2b

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "sunsethunter86/gemma-lite-e2b" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

gemma-lite-e2b / README.md

sunsethunter86

Upload README.md with huggingface_hub

3a8b5d7 verified 8 days ago

preview code

Raw

History Blame Contribute Delete

3.95 kB

metadata

license: gemma
license_link: https://ai.google.dev/gemma/terms
base_model: google/gemma-3n-E2B-it
tags:
  - gguf
  - llama.cpp
  - on-device
  - android
library_name: llama.cpp

Gemma LITE (E2B) — a smaller dictionary, the same mind

A Model Derivative of Google's Gemma 3n E2B, made for phones that cannot hold the original in memory.

Nothing about the model's reasoning was changed. All 35 transformer blocks are byte-for-byte the quantisation they started as. The only modification is to one tensor.

What was modified

per_layer_token_embd.weight — requantised from q6_K to q4_0, matching the precision of every layer that does the actual reasoning.

That single tensor is 57% of the original file: 1,837 MiB of a 3,179 MiB model, shaped [8960, 262144]. It is a lookup table — one row of about 7 KB is read per token — and it was stored at higher precision than the layers doing the thinking, every one of which is q4_0.

llama-quantize --allow-requantize \
  --tensor-type per_layer_token_embd=q4_0 \
  gemma-3n-E2B-it-q4_0.gguf gemma-lite-e2b-q4.gguf Q4_0

	file	`per_layer_token_embd`
source (E2B q4_0)	3.12 GiB	1,837 MiB (q6_K)
LITE	2.56 GiB	1,270 MiB (q4_0)

⚠️ A q2_K version of this model was published here and has been withdrawn

An earlier build took the same tensor down to q2_K, reaching 2.04 GiB. It passed a single-turn audition and failed badly over a real conversation. It was replaced on 2026-08-12 and should not be used.

Over 30 turns, q2_K against this q4_0 build:

	q2_K (withdrawn)	q4_0 (this file)
repetition, second half (4-gram overlap)	0.175, peaking 0.43	0.000
replies containing malformed control tokens	17 of 30	3 of 30
corrupted words (`It't what it is`)	throughout	none
latency, second half	5,600 ms	3,963 ms

q2_K collapsed into a verbal tic — "That's what it is" in nearly every reply after turn 12 — emitted malformed control tokens such as <end_of_of_turn> into visible output, and confidently misremembered the conversation it was in.

☠️ The lesson, if you are quantising embeddings yourself: a single-turn test cannot see this. The damage only appears once enough context has to be held at once. Test over a long conversation, not one reply.

Measured

Galaxy S22 Ultra (8 GB): the unmodified model was killed by Android's low-memory killer eleven times and never finished loading.

ROG Phone 8 Pro, llama.cpp with OpenCL, 8192 context:


unevictable (anonymous) memory	~178 MiB
GPU / shmem	~80 MiB
prompt eval	211 tok/s
generation	10.7 tok/s

A ~3,800-token system prompt prefills in about 18 seconds.

☠️ The GPU path is not an optimisation — it is why this fits. On CPU the same model holds 1,642 MiB of unevictable memory, roughly 9× more, which is the shape of failure that killed the unmodified model on 8 GB.

Quality

☠️ No perplexity or standardised benchmark has been run. What exists is a 30-turn conversational soak and a 17-prompt content probe, both single-sample. If you need measured quality, measure it.

Note the numbers above are for this file at 4,300 tokens of context; behaviour at the full 8,192 has not been characterised.

What it cannot do

The source GGUF carries no vision or audio encoder tensors, so this is a text-only model. Gemma 3n's image and audio input paths are not present.

Licence

Gemma 3n is provided under and subject to the Gemma Terms of Use: https://ai.google.dev/gemma/terms

This is a modified version. The modification is described above and is limited to the requantisation of a single tensor. The Gemma Terms, including the Prohibited Use Policy, apply to this derivative and to anything derived from it.

Base model: google/gemma-3n-E2B-it.