Instructions to use arelath/Meta-Llama-3-8B-Instruct-nanoquant-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 arelath/Meta-Llama-3-8B-Instruct-nanoquant-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 arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF
# Run inference directly in the terminal:
llama cli -hf arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF
# Run inference directly in the terminal:
llama cli -hf arelath/Meta-Llama-3-8B-Instruct-nanoquant-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 arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF
# Run inference directly in the terminal:
./llama-cli -hf arelath/Meta-Llama-3-8B-Instruct-nanoquant-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 arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF

Use Docker

docker model run hf.co/arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF

LM Studio
Jan

vLLM

How to use arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arelath/Meta-Llama-3-8B-Instruct-nanoquant-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": "arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF

Ollama
How to use arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF with Ollama:
```
ollama run hf.co/arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF
```

Unsloth Studio

How to use arelath/Meta-Llama-3-8B-Instruct-nanoquant-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 arelath/Meta-Llama-3-8B-Instruct-nanoquant-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 arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF to start chatting

Docker Model Runner
How to use arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF with Docker Model Runner:
```
docker model run hf.co/arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF
```

Lemonade

How to use arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF

Run and chat with the model

lemonade run user.Meta-Llama-3-8B-Instruct-nanoquant-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

Experiment 27: meta-llama/Meta-Llama-3-8B-Instruct quality benchmark

Status: completed
Model: meta-llama/Meta-Llama-3-8B-Instruct
Revision: 8afb486c1db24fe5011ec46dfbe5b5dccdb575c2
Candidate run: /workspace/NanoQuant/evidence/027/027-compress-and-benchmark-meta-llama-3-8b-instruct
Backend: dense
Wall time: 141.53 seconds

completed means all evaluators returned finite metrics; it is not a BF16-quality acceptance gate.

Protocol

WikiText-2: 64 samples × 128 tokens, batch 8
WikiText token hash: sha256:c7dc8810186996593a9a8a419db6bcae8e67e520c2412722425817fc5862a77d
Tasks: piqa, arc_easy, arc_challenge, hellaswag, winogrande, boolq; first 200 rows, batch 4
Tokenizer hash: sha256:8aa3159f5493d3660d5f6898b3b1a88d5b1626e4ac1f7dd5b60fed8f916080df

Quality results

Benchmark	Metric	BF16	NanoQuant	Delta	Ratio
WikiText-2	perplexity ↓	24.956664	55.331093	+30.374429 (+121.71%)	2.2171x
piqa	acc_norm ↑	0.7700	0.6800	-0.0900	0.8831x
arc_easy	acc_norm ↑	0.7550	0.4850	-0.2700	0.6424x
arc_challenge	acc_norm ↑	0.5150	0.2900	-0.2250	0.5631x
hellaswag	acc_norm ↑	0.6550	0.5500	-0.1050	0.8397x
winogrande	acc ↑	0.7150	0.6350	-0.0800	0.8881x
boolq	acc ↑	0.8300	0.7400	-0.0900	0.8916x

Runtime and memory

Model	Elapsed seconds	Peak CUDA bytes	Peak host bytes
BF16	29.73	18,194,890,752	33,399,840,768
NanoQuant	35.35	18,803,064,832	33,399,840,768

Provenance

Experiment config hash: sha256:801c828f06b50662d77573ed177f639142880d06b9d4f440261babe50ab94b96
Launcher: experiments/027-compress-and-benchmark-meta-llama-3-8b-instruct.py
Candidate identity: {"config_hash":"sha256:044785fa22c02ddeb31c43cffde7172becdc19475a8e342b0a8344613a6ef2fb","model_hash":"sha256:d590dbc8c4a1851df6feb003b377003e7e4ededacc99ed35abb96844d236322d","plan_hash":"sha256-57b3f751fb9b821e18abad776ffc22f4f90d5b6d73378e90037728ca2b1cdcbb"}
Global tuning: {"artifact_id":"sha256-68defbc90a8e75e2a59b51d40c054cff9bc393012039641fa3365b32787509e7","artifact_type":"global-tuning-result","schema_version":1}

Downloads last month: 225

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for arelath/Meta-Llama-3-8B-Instruct-nanoquant-GGUF

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Quantized

(277)

this model