Instructions to use flohannes/mistral-7b-instruct-4bit-1k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flohannes/mistral-7b-instruct-4bit-1k with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("flohannes/mistral-7b-instruct-4bit-1k")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

llama-cpp-python

How to use flohannes/mistral-7b-instruct-4bit-1k with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="flohannes/mistral-7b-instruct-4bit-1k",
	filename="mistral-7b-instr-v1-1100.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 flohannes/mistral-7b-instruct-4bit-1k with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf flohannes/mistral-7b-instruct-4bit-1k
# Run inference directly in the terminal:
llama-cli -hf flohannes/mistral-7b-instruct-4bit-1k

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf flohannes/mistral-7b-instruct-4bit-1k
# Run inference directly in the terminal:
llama-cli -hf flohannes/mistral-7b-instruct-4bit-1k

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 flohannes/mistral-7b-instruct-4bit-1k
# Run inference directly in the terminal:
./llama-cli -hf flohannes/mistral-7b-instruct-4bit-1k

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 flohannes/mistral-7b-instruct-4bit-1k
# Run inference directly in the terminal:
./build/bin/llama-cli -hf flohannes/mistral-7b-instruct-4bit-1k

Use Docker

docker model run hf.co/flohannes/mistral-7b-instruct-4bit-1k

LM Studio
Jan

vLLM

How to use flohannes/mistral-7b-instruct-4bit-1k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flohannes/mistral-7b-instruct-4bit-1k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flohannes/mistral-7b-instruct-4bit-1k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/flohannes/mistral-7b-instruct-4bit-1k

Ollama
How to use flohannes/mistral-7b-instruct-4bit-1k with Ollama:
```
ollama run hf.co/flohannes/mistral-7b-instruct-4bit-1k
```

Unsloth Studio

How to use flohannes/mistral-7b-instruct-4bit-1k 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 flohannes/mistral-7b-instruct-4bit-1k 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 flohannes/mistral-7b-instruct-4bit-1k to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for flohannes/mistral-7b-instruct-4bit-1k to start chatting

MLX LM

How to use flohannes/mistral-7b-instruct-4bit-1k with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "flohannes/mistral-7b-instruct-4bit-1k"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "flohannes/mistral-7b-instruct-4bit-1k"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "flohannes/mistral-7b-instruct-4bit-1k",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use flohannes/mistral-7b-instruct-4bit-1k with Docker Model Runner:
```
docker model run hf.co/flohannes/mistral-7b-instruct-4bit-1k
```

Lemonade

How to use flohannes/mistral-7b-instruct-4bit-1k with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull flohannes/mistral-7b-instruct-4bit-1k

Run and chat with the model

lemonade run user.mistral-7b-instruct-4bit-1k-{{QUANT_TAG}}

List all available models

lemonade list

flohannes/mistral-7b-instruct-4bit-1k

The Model flohannes/mistral-7b-instruct-4bit-1k was converted to MLX format from mlx-community/Mistral-7B-Instruct-v0.2-4bit using mlx-lm version 0.17.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("flohannes/mistral-7b-instruct-4bit-1k")
response = generate(model, tokenizer, prompt="hello", verbose=True)

Downloads last month: 17

Safetensors

Model size

1B params

Tensor type

F16

U32

MLX

Hardware compatibility

Quantized