Instructions to use tensorblock/mt0-xxl-mt-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/mt0-xxl-mt-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/mt0-xxl-mt-GGUF",
	filename="mt0-xxl-mt-Q2_K.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 tensorblock/mt0-xxl-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 tensorblock/mt0-xxl-mt-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/mt0-xxl-mt-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/mt0-xxl-mt-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/mt0-xxl-mt-GGUF:Q2_K

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 tensorblock/mt0-xxl-mt-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/mt0-xxl-mt-GGUF:Q2_K

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 tensorblock/mt0-xxl-mt-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/mt0-xxl-mt-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/mt0-xxl-mt-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/mt0-xxl-mt-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/mt0-xxl-mt-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/mt0-xxl-mt-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tensorblock/mt0-xxl-mt-GGUF:Q2_K

Ollama
How to use tensorblock/mt0-xxl-mt-GGUF with Ollama:
```
ollama run hf.co/tensorblock/mt0-xxl-mt-GGUF:Q2_K
```

Unsloth Studio new

How to use tensorblock/mt0-xxl-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 tensorblock/mt0-xxl-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 tensorblock/mt0-xxl-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 tensorblock/mt0-xxl-mt-GGUF to start chatting

Docker Model Runner
How to use tensorblock/mt0-xxl-mt-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/mt0-xxl-mt-GGUF:Q2_K
```

Lemonade

How to use tensorblock/mt0-xxl-mt-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/mt0-xxl-mt-GGUF:Q2_K

Run and chat with the model

lemonade run user.mt0-xxl-mt-GGUF-Q2_K

List all available models

lemonade list

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

bigscience/mt0-xxl-mt - GGUF

This repo contains GGUF format model files for bigscience/mt0-xxl-mt.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit ec7f3ac.

Our projects

Forge

An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio

A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

Model file specification

Filename	Quant type	File Size	Description
mt0-xxl-mt-Q2_K.gguf	Q2_K	5.079 GB	smallest, significant quality loss - not recommended for most purposes
mt0-xxl-mt-Q3_K_S.gguf	Q3_K_S	5.960 GB	very small, high quality loss
mt0-xxl-mt-Q3_K_M.gguf	Q3_K_M	6.397 GB	very small, high quality loss
mt0-xxl-mt-Q3_K_L.gguf	Q3_K_L	6.791 GB	small, substantial quality loss
mt0-xxl-mt-Q4_0.gguf	Q4_0	7.540 GB	legacy; small, very high quality loss - prefer using Q3_K_M
mt0-xxl-mt-Q4_K_S.gguf	Q4_K_S	7.564 GB	small, greater quality loss
mt0-xxl-mt-Q4_K_M.gguf	Q4_K_M	8.085 GB	medium, balanced quality - recommended
mt0-xxl-mt-Q5_0.gguf	Q5_0	9.027 GB	legacy; medium, balanced quality - prefer using Q4_K_M
mt0-xxl-mt-Q5_K_S.gguf	Q5_K_S	9.027 GB	large, low quality loss - recommended
mt0-xxl-mt-Q5_K_M.gguf	Q5_K_M	9.308 GB	large, very low quality loss - recommended
mt0-xxl-mt-Q6_K.gguf	Q6_K	10.607 GB	very large, extremely low quality loss
mt0-xxl-mt-Q8_0.gguf	Q8_0	13.736 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/mt0-xxl-mt-GGUF --include "mt0-xxl-mt-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/mt0-xxl-mt-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'

Downloads last month: 67

GGUF

Model size

13B params

Architecture

Hardware compatibility

2-bit

3-bit

Model tree for tensorblock/mt0-xxl-mt-GGUF

Base model

bigscience/mt0-xxl-mt

Quantized

(3)

this model

Datasets used to train tensorblock/mt0-xxl-mt-GGUF

Evaluation results

Accuracy on Winogrande XL (xl)
validation set self-reported

62.670
Accuracy on XWinograd (en)
test set self-reported

83.310
Accuracy on XWinograd (fr)
test set self-reported

78.310
Accuracy on XWinograd (jp)
test set self-reported

80.190
Accuracy on XWinograd (pt)
test set self-reported

80.990
Accuracy on XWinograd (ru)
test set self-reported

79.050
Accuracy on XWinograd (zh)
test set self-reported

82.340
Accuracy on ANLI (r1)
validation set self-reported

49.500