Instructions to use thirteenbit/madlad400-10b-mt-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thirteenbit/madlad400-10b-mt-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="thirteenbit/madlad400-10b-mt-gguf",
	filename="model-q3_k_m.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use thirteenbit/madlad400-10b-mt-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf thirteenbit/madlad400-10b-mt-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf thirteenbit/madlad400-10b-mt-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf thirteenbit/madlad400-10b-mt-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf thirteenbit/madlad400-10b-mt-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 thirteenbit/madlad400-10b-mt-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf thirteenbit/madlad400-10b-mt-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 thirteenbit/madlad400-10b-mt-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf thirteenbit/madlad400-10b-mt-gguf:Q4_K_M

Use Docker

docker model run hf.co/thirteenbit/madlad400-10b-mt-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use thirteenbit/madlad400-10b-mt-gguf with Ollama:
```
ollama run hf.co/thirteenbit/madlad400-10b-mt-gguf:Q4_K_M
```

Unsloth Studio new

How to use thirteenbit/madlad400-10b-mt-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 thirteenbit/madlad400-10b-mt-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 thirteenbit/madlad400-10b-mt-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for thirteenbit/madlad400-10b-mt-gguf to start chatting

Docker Model Runner
How to use thirteenbit/madlad400-10b-mt-gguf with Docker Model Runner:
```
docker model run hf.co/thirteenbit/madlad400-10b-mt-gguf:Q4_K_M
```

Lemonade

How to use thirteenbit/madlad400-10b-mt-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull thirteenbit/madlad400-10b-mt-gguf:Q4_K_M

Run and chat with the model

lemonade run user.madlad400-10b-mt-gguf-Q4_K_M

List all available models

lemonade list

MADLAD-400-10B-MT - GGUF

Original model: MADLAD-400-10B-MT

Description

This repo contains GGUF format model files for MADLAD-400-10B-MT for use with llama.cpp and compatible software.

Converted to gguf using llama.cpp convert_hf_to_gguf.py and quantized using llama.cpp llama-quantize, llama.cpp version b3325.

Provided files

Name	Quant method	Bits	Size	VRAM required
model-q3_k_m.gguf	Q3_K_M	3	4.9 GB	5.7 GB
model-q4_k_m.gguf	Q4_K_M	4	6.3 GB	7.1 GB
model-q5_k_m.gguf	Q5_K_M	5	7.2 GB	7.9 GB
model-q6_k.gguf	Q6_K	6	8.2 GB	8.9 GB
model-q8_0.gguf	Q8_0	8	11 GB	11.3 GB

Note: the above VRAM usage figures are observed with all layers GPU offloading, on Linux with NVIDIA GPU.

Downloads last month: 160

GGUF

Model size

11B params

Architecture

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for thirteenbit/madlad400-10b-mt-gguf

Base model

google/madlad400-10b-mt

Quantized

(11)

this model