Instructions to use TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF 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 TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16

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 TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16

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 TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16

Use Docker

docker model run hf.co/TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16

LM Studio
Jan
Ollama
How to use TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF with Ollama:
```
ollama run hf.co/TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16
```
Unsloth Desktop

How to use TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF with Docker Model Runner:
```
docker model run hf.co/TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16
```

Lemonade

How to use TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16

Run and chat with the model

lemonade run user.Gemma-4-E4B-IT-Sumtablets-GGUF-BF16

List all available models

lemonade list

Hermes Agent

How to use TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16

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 TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16

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 "TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF:BF16" \
  --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-4-E4B-IT-Sumtablets-GGUF

Gemma 4 E4B-IT fine-tuned for Sumerian cuneiform transliteration — converting glyph name sequences into standard Latin-alphabet transliterations as used in Assyriology.

Trained on the SumTablets dataset (82,452 administrative texts, predominantly Ur III period) using QLoRA via Unsloth.

Task

Given a sequence of Sumerian cuneiform glyph names (e.g., 1(diš) 1(aš) gur še lugal), the model produces the corresponding transliteration in standard Assyriological convention.

This is a structured sequence-to-sequence translation task — not free-form text generation. The model must learn the compositional rules of Sumerian sign reading, including:

Determinatives (e.g., d, diš)
Logographic vs. syllabic sign readings
Numeric notation systems (Š, N, etc.)
Signs with multiple possible readings

Training Details

Parameter	Value
Base Model	`unsloth/gemma-4-E4B-it` (4-bit QLoRA)
Dataset	`colesimmons/SumTablets` (82,452 train / 4,577 val / 4,577 test)
Format Mapping	`glyph_names → user`, `transliteration → assistant`
System Prompt	"Transliterate the following Sumerian cuneiform glyph names into their corresponding Latin alphabet transliteration. Output ONLY the transliteration."
LoRA Rank	16
LoRA Alpha	16 (rsLoRA enabled)
Learning Rate	5e-5
Scheduler	Cosine
Batch Size	2 × 8 accum = 16 effective
Max Seq Length	4096
train_on_completions	false
packing	false
Hardware	NVIDIA RTX 5080 (16GB)

Results

Metric	Value
Train Loss (optimal)	0.30
Character Accuracy	36.2%

The 36% character-level accuracy reflects the inherent difficulty of the task — Sumerian sign readings are heavily context-dependent, with many signs having 5+ valid readings depending on genre, period, and surrounding signs. The model performs strongest on short administrative texts (Ur III, ~93% of training data) and weakest on long literary compositions.

Note on inference: Gemma-4-E4B's built-in thinking/reasoning mode can override the fine-tuned transliteration behavior. Use the same system prompt during inference as was used during training to suppress reasoning mode and get clean transliteration output.

GGUF Quantizations

File	Format	Size	Use Case
`gemma-4-e4b-it.Q4_K_M.gguf`	Q4_K_M	4.97 GB	General use — best quality/size balance
`gemma-4-e4b-it.BF16-mmproj.gguf`	BF16	374 MB	Multimodal projector (required for vision input)

Usage

llama.cpp / LM Studio

llama-cli \
  -m gemma-4-e4b-it.Q4_K_M.gguf \
  --system-prompt "Transliterate the following Sumerian cuneiform glyph names into their corresponding Latin alphabet transliteration. Output ONLY the transliteration." \
  -p "1(diš) gin₂ ku₃-babbar"

llama-server (OpenAI-compatible)

llama-server \
  -m gemma-4-e4b-it.Q4_K_M.gguf \
  --system-prompt "Transliterate the following Sumerian cuneiform glyph names into their corresponding Latin alphabet transliteration. Output ONLY the transliteration."

Limitations

Domain concentration: 93% of training data is administrative texts from the Ur III period. Performance degrades on literary, lexical, or other period texts.
Character accuracy ceiling: 36% char-level accuracy means roughly 1 in 3 characters will be incorrect — suitable as a pre-processing/assistive tool, not as a standalone authoritative transliteration.
Thinking mode interference: Without the system prompt, the base model's reasoning mode may produce English analysis instead of transliteration.
No audio/vision evaluation: The multimodal projector weights are included but were not evaluated for image-to-text cuneiform reading.

Dataset

Training used colesimmons/SumTablets (CC-BY-4.0):

82,452 training samples, 4,577 validation, 4,577 test
Columns: glyph_names (input) → transliteration (target)
Predominantly Ur III period administrative records
Covers genres: administrative, legal, letter, literary, lexical, royal inscription, school text

Acknowledgments

Google DeepMind — Gemma 4 model family
Colesimmons — SumTablets dataset
Unsloth — QLoRA training framework (2× faster fine-tuning)

License

Apache 2.0 — see Gemma 4 License for model terms. Dataset licensed separately under CC-BY-4.0.

Downloads last month: 31

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

4-bit

Model tree for TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(349)

this model

Dataset used to train TRACCERR/Gemma-4-E4B-IT-Sumtablets-GGUF

Evaluation results

Train Loss (optimal stopping point) on colesimmons/SumTablets
test set self-reported

0.300
Character-Level Accuracy on colesimmons/SumTablets
test set self-reported

36.200