Instructions to use efficiencyx/Jun-LoRA-E2B-MTP-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 efficiencyx/Jun-LoRA-E2B-MTP-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 efficiencyx/Jun-LoRA-E2B-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf efficiencyx/Jun-LoRA-E2B-MTP-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf efficiencyx/Jun-LoRA-E2B-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf efficiencyx/Jun-LoRA-E2B-MTP-GGUF: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 efficiencyx/Jun-LoRA-E2B-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf efficiencyx/Jun-LoRA-E2B-MTP-GGUF: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 efficiencyx/Jun-LoRA-E2B-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf efficiencyx/Jun-LoRA-E2B-MTP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/efficiencyx/Jun-LoRA-E2B-MTP-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use efficiencyx/Jun-LoRA-E2B-MTP-GGUF with Ollama:
```
ollama run hf.co/efficiencyx/Jun-LoRA-E2B-MTP-GGUF:Q4_K_M
```
Unsloth Desktop

How to use efficiencyx/Jun-LoRA-E2B-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf efficiencyx/Jun-LoRA-E2B-MTP-GGUF: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": "efficiencyx/Jun-LoRA-E2B-MTP-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use efficiencyx/Jun-LoRA-E2B-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/efficiencyx/Jun-LoRA-E2B-MTP-GGUF:Q4_K_M
```

Lemonade

How to use efficiencyx/Jun-LoRA-E2B-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull efficiencyx/Jun-LoRA-E2B-MTP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Jun-LoRA-E2B-MTP-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use efficiencyx/Jun-LoRA-E2B-MTP-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 efficiencyx/Jun-LoRA-E2B-MTP-GGUF: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 efficiencyx/Jun-LoRA-E2B-MTP-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use efficiencyx/Jun-LoRA-E2B-MTP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf efficiencyx/Jun-LoRA-E2B-MTP-GGUF: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 "efficiencyx/Jun-LoRA-E2B-MTP-GGUF: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"

Jun-LoRA-E2B-MTP-GGUF

MTP / speculative-decoding draft model for efficiencyx/Jun-LoRA-E2B-GGUF. Not a chat model, it only proposes tokens that Jun then verifies.

This is Google's stock drafter, not one trained on Jun. The weights are google/gemma-4-E2B-it-qat-q4_0-unquantized-assistant unchanged, converted to GGUF and quantized to Q4_K_M. Fine-tuning a drafter on Jun (tried on E4B) did not beat stock in llama.cpp, so this repo just puts the stock one where JunOS looks for it: the chat repo's name with -MTP added, same quant tag.

gemma-4-E2B-it-qat-assistant-Q4_K_M.gguf, 76 MB, Q4_K_M
QAT branch, matching Jun's base (unsloth/gemma-4-E2B-it-qat-q4_0-unquantized). A drafter from the non-QAT branch loads fine and guesses much worse.
Tensors, shapes and architecture metadata are identical to the Q8_0 conversion that llama.cpp already serves, only the quant types differ.

Use

JunOS's ./mtp-autotune.sh falls back to it when OLLAMA_MTP is empty. With llama.cpp directly:

llama-server -m Jun-LoRA-E2B.Q4_K_M.gguf \
  --spec-type draft-mtp --spec-draft-model gemma-4-E2B-it-qat-assistant-Q4_K_M.gguf --spec-draft-n-max 1

Made with

llama.cpp 8e7f22b:

python convert_hf_to_gguf.py gemma-4-E2B-it-qat-q4_0-unquantized-assistant \
  --outtype bf16 --outfile gemma-4-E2B-it-qat-assistant-BF16.gguf
llama-quantize gemma-4-E2B-it-qat-assistant-BF16.gguf gemma-4-E2B-it-qat-assistant-Q4_K_M.gguf Q4_K_M

Downloads last month: 66

GGUF

Model size

77.2M params

Architecture

gemma4-assistant

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for efficiencyx/Jun-LoRA-E2B-MTP-GGUF

Base model

google/gemma-4-E2B-it-assistant

Finetuned

google/gemma-4-E2B-it-qat-q4_0-unquantized-assistant

Quantized

(13)

this model