Instructions to use mobilint/Llama-3.1-8B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mobilint/Llama-3.1-8B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mobilint/Llama-3.1-8B-Instruct-GGUF",
	filename="llama-3.1-8b-instruct-vocab.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mobilint/Llama-3.1-8B-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mobilint/Llama-3.1-8B-Instruct-GGUF
# Run inference directly in the terminal:
llama-cli -hf mobilint/Llama-3.1-8B-Instruct-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mobilint/Llama-3.1-8B-Instruct-GGUF
# Run inference directly in the terminal:
llama-cli -hf mobilint/Llama-3.1-8B-Instruct-GGUF

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 mobilint/Llama-3.1-8B-Instruct-GGUF
# Run inference directly in the terminal:
./llama-cli -hf mobilint/Llama-3.1-8B-Instruct-GGUF

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 mobilint/Llama-3.1-8B-Instruct-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mobilint/Llama-3.1-8B-Instruct-GGUF

Use Docker

docker model run hf.co/mobilint/Llama-3.1-8B-Instruct-GGUF

LM Studio
Jan

vLLM

How to use mobilint/Llama-3.1-8B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mobilint/Llama-3.1-8B-Instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mobilint/Llama-3.1-8B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mobilint/Llama-3.1-8B-Instruct-GGUF

Ollama
How to use mobilint/Llama-3.1-8B-Instruct-GGUF with Ollama:
```
ollama run hf.co/mobilint/Llama-3.1-8B-Instruct-GGUF
```

Unsloth Studio

How to use mobilint/Llama-3.1-8B-Instruct-GGUF 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 mobilint/Llama-3.1-8B-Instruct-GGUF 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 mobilint/Llama-3.1-8B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mobilint/Llama-3.1-8B-Instruct-GGUF to start chatting

How to use mobilint/Llama-3.1-8B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mobilint/Llama-3.1-8B-Instruct-GGUF

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": "mobilint/Llama-3.1-8B-Instruct-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mobilint/Llama-3.1-8B-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mobilint/Llama-3.1-8B-Instruct-GGUF

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 mobilint/Llama-3.1-8B-Instruct-GGUF

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use mobilint/Llama-3.1-8B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/mobilint/Llama-3.1-8B-Instruct-GGUF
```

Lemonade

How to use mobilint/Llama-3.1-8B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mobilint/Llama-3.1-8B-Instruct-GGUF

Run and chat with the model

lemonade run user.Llama-3.1-8B-Instruct-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Llama 3.1 8B Instruct — GGUF + MXQ for llama-cli-mblt

This repository provides Llama 3.1 8B Instruct compiled and optimized for Mobilint NPU hardware, packaged for use with llama-cli-mblt.

Branches

Branch	Contents	Description
`main`	Body model only	Standard autoregressive decoding
`eagle3`	Body + FC + Draft models	EAGLE3 speculative decoding (~2-4x faster)

Files

main branch

File	Size	Description
`llama-3.1-8b-instruct-vocab.gguf`	7.5 MB	Tokenizer (vocab-only GGUF)
`target_emb.bin`	2.0 GB	Body embedding weights (float32)
`single_Body_Llama-3.1-8B-Instruct.mxq`	3.7 GB	Body model for NPU (W4V8 quantized)
`config.json`	—	Model configuration

eagle3 branch (adds)

File	Size	Description
`single_Fc_Llama-3.1-8B-Instruct.mxq`	49 MB	FC dimension converter model
`Draft_Llama-3.1-8B-Instruct.mxq`	181 MB	EAGLE3 draft model
`draft_emb.bin`	2.0 GB	Draft embedding weights
`d2t.bin`	250 KB	Draft-to-target vocabulary mapping

Quick Start

Install

# Build llama-cli-mblt
cd llama.cpp
cmake -B build -DLLAMA_MOBILINT=ON -DLLAMA_MOBILINT_RUNTIME_DIR=/path/to/qbruntime -DCMAKE_BUILD_TYPE=Release
cmake --build build --target llama-cli-mblt -j$(nproc)

Simple decoding (main branch)

# Download model files
huggingface-cli download mobilint/Llama-3.1-8B-Instruct-GGUF --local-dir models/llama-8b

# Run
./build/bin/llama-cli-mblt \
    --gguf  models/llama-8b/llama-3.1-8b-instruct-vocab.gguf \
    --embd  models/llama-8b/target_emb.bin \
    --mxq   models/llama-8b/single_Body_Llama-3.1-8B-Instruct.mxq \
    --core-mode global4 --chat \
    -p "What is the meaning of life?" -n 256

EAGLE3 speculative decoding (eagle3 branch)

# Download with eagle3 branch
huggingface-cli download mobilint/Llama-3.1-8B-Instruct-GGUF --revision eagle3 --local-dir models/llama-8b-eagle3

# Run with ~2-4x speedup
./build/bin/llama-cli-mblt \
    --gguf  models/llama-8b-eagle3/llama-3.1-8b-instruct-vocab.gguf \
    --embd  models/llama-8b-eagle3/target_emb.bin \
    --mxq   models/llama-8b-eagle3/single_Body_Llama-3.1-8B-Instruct.mxq \
    --mxq-fc    models/llama-8b-eagle3/single_Fc_Llama-3.1-8B-Instruct.mxq \
    --mxq-draft models/llama-8b-eagle3/Draft_Llama-3.1-8B-Instruct.mxq \
    --embd-draft models/llama-8b-eagle3/draft_emb.bin \
    --d2t   models/llama-8b-eagle3/d2t.bin \
    --core-mode global4 --n-draft 2 --tree-depth 6 --total-tokens 23 \
    --chat --temp 0.0 -p "Explain quantum computing" -n 200

# Interactive chat
./build/bin/llama-cli-mblt \
    --gguf  models/llama-8b-eagle3/llama-3.1-8b-instruct-vocab.gguf \
    --embd  models/llama-8b-eagle3/target_emb.bin \
    --mxq   models/llama-8b-eagle3/single_Body_Llama-3.1-8B-Instruct.mxq \
    --mxq-fc    models/llama-8b-eagle3/single_Fc_Llama-3.1-8B-Instruct.mxq \
    --mxq-draft models/llama-8b-eagle3/Draft_Llama-3.1-8B-Instruct.mxq \
    --embd-draft models/llama-8b-eagle3/draft_emb.bin \
    --d2t   models/llama-8b-eagle3/d2t.bin \
    --core-mode global4 --n-draft 2 --tree-depth 6 --total-tokens 23 \
    -i -n 256