Instructions to use TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF", dtype="auto")

llama-cpp-python

How to use TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF",
	filename="mixtral-8x7b-instruct-v0.1.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheBloke/Mixtral-8x7B-Instruct-v0.1-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 TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheBloke/Mixtral-8x7B-Instruct-v0.1-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 TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheBloke/Mixtral-8x7B-Instruct-v0.1-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 TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF with Ollama:
```
ollama run hf.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M
```

Unsloth Studio

How to use TheBloke/Mixtral-8x7B-Instruct-v0.1-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 TheBloke/Mixtral-8x7B-Instruct-v0.1-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 TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF to start chatting

Docker Model Runner
How to use TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF with Docker Model Runner:
```
docker model run hf.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M
```

Lemonade

How to use TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Mixtral-8x7B-Instruct-v0.1-GGUF-Q4_K_M

List all available models

lemonade list

New discussion

Resources

View closed (5)

Request: Updated Mixtral GGUF (Q6_K or Q5_K_M) with full MoE tensor support for LM Studio (post-Jan 2025)

#33 opened 8 months ago by

ThomasL71

Report

#32 opened about 1 year ago by

ratboy1

USE

#31 opened about 1 year ago by

HOSEINvahdati

fail

👍 1

#30 opened over 1 year ago by

ratboy1

How do you estimate the number of GPUs required to run this model?

#29 opened about 2 years ago by

vishjoshi

Ollama Modelfile

#28 opened about 2 years ago by

noix

Help: CUDA out of memory. Hardware Requirments.

#27 opened over 2 years ago by

zebfreeman

CUDA error: the provided PTX was compiled with an unsupported toolchain.

👍 1

#26 opened over 2 years ago by

parvezkhan

THANK YOU!!

#25 opened over 2 years ago by

bobba84

No K_S models?

#24 opened over 2 years ago by

Nafnlaus

Hardware Requirements for Q4_K_M

#23 opened over 2 years ago by

ShivanshMathur007

Can we finetune this gguf model for our custom need

👍 1

#22 opened over 2 years ago by

auralodyssey

Download Error when deploying to SageMaker

#21 opened over 2 years ago by

csanchez-aureum

Getting runtime error when loading with llama-cpp in a HF space with Nvidia A10G Large

#20 opened over 2 years ago by

Isaid-Silver

Q6_K version is broken

#19 opened over 2 years ago by

tankstarwar

Snake.py with pygame works!!

👍 2

#16 opened over 2 years ago by

robert1968

Works with with the current oobabooga version.

#15 opened over 2 years ago by

robert1968

Issue with GPU Utilization in Colab Notebook

#14 opened over 2 years ago by

Sagar3745

Update README.md

#13 opened over 2 years ago by

pavben

8x7B (Q3) vs 7B

#12 opened over 2 years ago by

vidyamantra

Update README.md

#10 opened over 2 years ago by

MaZeNsMz

Why is the response slower than the 70B model?

#9 opened over 2 years ago by

shalene

Even this excellent high-end model doesn't follow my instructions

#8 opened over 2 years ago by

alexcardo

Behaviour with AMD GPU offload?

#7 opened over 2 years ago by

thigger

chatbot giving weird responses

#6 opened over 2 years ago by

hammad93

KCPP frankenstein experimental release for Mixtral

❤️👍 1

#5 opened over 2 years ago by

Nexesenex

Issue with Mixtral-8x7B-Instruct-v0.1-GGUF Model: 'blk.0.ffn_gate.weight' Tensor Not Found

#4 opened over 2 years ago by

littleworth

error

#3 opened over 2 years ago by

LaferriereJC

WOW - best opensource llm I ever seen !

🤯👍 15

#1 opened over 2 years ago by

mirek190