Instructions to use lthn/lemma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use lthn/lemma 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 lthn/lemma:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lthn/lemma:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lthn/lemma:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lthn/lemma:Q4_K_M

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 lthn/lemma:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lthn/lemma:Q4_K_M

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 lthn/lemma:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lthn/lemma:Q4_K_M

Use Docker

docker model run hf.co/lthn/lemma:Q4_K_M

LM Studio
Jan

vLLM

How to use lthn/lemma with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lthn/lemma"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lthn/lemma",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/lthn/lemma:Q4_K_M

Ollama
How to use lthn/lemma with Ollama:
```
ollama run hf.co/lthn/lemma:Q4_K_M
```
Unsloth Desktop

How to use lthn/lemma with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lthn/lemma:Q4_K_M

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": "lthn/lemma:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use lthn/lemma with Docker Model Runner:
```
docker model run hf.co/lthn/lemma:Q4_K_M
```

Lemonade

How to use lthn/lemma with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lthn/lemma:Q4_K_M

Run and chat with the model

lemonade run user.lemma-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use lthn/lemma with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lthn/lemma:Q4_K_M

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 lthn/lemma:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use lthn/lemma with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lthn/lemma:Q4_K_M

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 "lthn/lemma:Q4_K_M" \
  --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"

Snider Virgil commited on Apr 11

Commit

95a8db5

1 Parent(s): 733d141

docs: correct base_model lineage for HF model tree

Browse files

HF uses base_model + base_model_relation frontmatter to rank models in
search results and render the model tree widget. The Lemma family's
true lineage is:

google/gemma-4-*-it
└── LetheanNetwork/<m> (finetune — our namespace fork)
└── lthn/<m> (finetune — LEK merged into weights)
└── lthn/<m>-mlx (quantized — mlx 4/8bit/bf16)

Previously this repo had base_model_relation set to quantized, which
was wrong — LEK merging is a finetune, not a quant. Fixing so the
model tree widget ranks the family correctly.

Co-Authored-By: Virgil <virgil@lethean.io>

Files changed (1) hide show

README.md +12 -12

README.md CHANGED Viewed

@@ -3,19 +3,19 @@ license: eupl-1.2
 pipeline_tag: image-text-to-text
 library_name: gguf
 base_model:
-  - LetheanNetwork/lemma
-base_model_relation: quantized
 tags:
-  - gemma4
-  - lemma
-  - gguf
-  - llama.cpp
-  - ollama
-  - multimodal
-  - vision
-  - audio
-  - on-device
-  - conversational
 ---
 <!--
 This content is subject to the European Union Public Licence (EUPL-1.2).

 pipeline_tag: image-text-to-text
 library_name: gguf
 base_model:
+- LetheanNetwork/lemma
+base_model_relation: finetune
 tags:
+- gemma4
+- lemma
+- gguf
+- llama.cpp
+- ollama
+- multimodal
+- vision
+- audio
+- on-device
+- conversational
 ---
 <!--
 This content is subject to the European Union Public Licence (EUPL-1.2).