Instructions to use ikerion/mistral-7b-magyar-q4-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ikerion/mistral-7b-magyar-q4-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ikerion/mistral-7b-magyar-q4-gguf",
	filename="mistral-magyar-q4.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ikerion/mistral-7b-magyar-q4-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ikerion/mistral-7b-magyar-q4-gguf
# Run inference directly in the terminal:
llama-cli -hf ikerion/mistral-7b-magyar-q4-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ikerion/mistral-7b-magyar-q4-gguf
# Run inference directly in the terminal:
llama-cli -hf ikerion/mistral-7b-magyar-q4-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 ikerion/mistral-7b-magyar-q4-gguf
# Run inference directly in the terminal:
./llama-cli -hf ikerion/mistral-7b-magyar-q4-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 ikerion/mistral-7b-magyar-q4-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ikerion/mistral-7b-magyar-q4-gguf

Use Docker

docker model run hf.co/ikerion/mistral-7b-magyar-q4-gguf

LM Studio
Jan
Ollama
How to use ikerion/mistral-7b-magyar-q4-gguf with Ollama:
```
ollama run hf.co/ikerion/mistral-7b-magyar-q4-gguf
```

Unsloth Studio

How to use ikerion/mistral-7b-magyar-q4-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 ikerion/mistral-7b-magyar-q4-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 ikerion/mistral-7b-magyar-q4-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ikerion/mistral-7b-magyar-q4-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use ikerion/mistral-7b-magyar-q4-gguf with Docker Model Runner:
```
docker model run hf.co/ikerion/mistral-7b-magyar-q4-gguf
```

Lemonade

How to use ikerion/mistral-7b-magyar-q4-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ikerion/mistral-7b-magyar-q4-gguf

Run and chat with the model

lemonade run user.mistral-7b-magyar-q4-gguf-{{QUANT_TAG}}

List all available models

lemonade list

Mistral 7B Magyar Q4 GGUF

Kvantált (Q4_0) magyar nyelvű Mistral 7B modell GGUF formátumban.

Modell részletek

Alap modell: Mistral 7B
Kvantálás: Q4_0 (4-bit)
Fájl méret: ~3.8 GB
Formátum: GGUF
Optimalizálva: NVIDIA Jetson eszközökre

Használat

llama.cpp-vel:

./main -m mistral-magyar-q4.gguf -p "Kérdés: Mi a főváros?" -n 128

Python-ban:

from llama_cpp import Llama

llm = Llama(
    model_path="mistral-magyar-q4.gguf",
    n_ctx=2048,
    n_threads=4
)

response = llm("Kérdés: Mi Budapest?", max_tokens=128)
print(response['choices'][0]['text'])

Hardver követelmények

RAM: Minimum 4 GB
Tárhely: 4 GB szabad hely
Optimális: NVIDIA Jetson vagy hasonló ARM64 platform

Licenc

Apache 2.0

Downloads last month: 11

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support