Instructions to use juvi21/Tess-3-7B-SFT-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use juvi21/Tess-3-7B-SFT-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf juvi21/Tess-3-7B-SFT-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf juvi21/Tess-3-7B-SFT-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf juvi21/Tess-3-7B-SFT-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf juvi21/Tess-3-7B-SFT-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 juvi21/Tess-3-7B-SFT-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf juvi21/Tess-3-7B-SFT-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 juvi21/Tess-3-7B-SFT-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf juvi21/Tess-3-7B-SFT-GGUF:Q4_K_M

Use Docker

docker model run hf.co/juvi21/Tess-3-7B-SFT-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use juvi21/Tess-3-7B-SFT-GGUF with Ollama:
```
ollama run hf.co/juvi21/Tess-3-7B-SFT-GGUF:Q4_K_M
```

Unsloth Studio

How to use juvi21/Tess-3-7B-SFT-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 juvi21/Tess-3-7B-SFT-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 juvi21/Tess-3-7B-SFT-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for juvi21/Tess-3-7B-SFT-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use juvi21/Tess-3-7B-SFT-GGUF with Docker Model Runner:
```
docker model run hf.co/juvi21/Tess-3-7B-SFT-GGUF:Q4_K_M
```

Lemonade

How to use juvi21/Tess-3-7B-SFT-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull juvi21/Tess-3-7B-SFT-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Tess-3-7B-SFT-GGUF-Q4_K_M

List all available models

lemonade list

Tess-3-7B-SFT-GGUF Quants

I used llama.cpp release b3166 for making several quants for the FLOP poor. Visit the OG model card for more details: https://huggingface.co/migtissera/Tess-3-7B-SFT

Quants

Filename	Quant type	File Size
Tess-3-7B-SFT-f16.gguf	F16	14.5 GB
Tess-3-7B-SFT-gguf-q8_0.gguf	Q8_0	7.7 GB
Tess-3-7B-SFT-gguf-q6_k.gguf	Q6_K	5.95 GB
Tess-3-7B-SFT-gguf-q5_k_s.gguf	Q5_K_S	5 GB
Tess-3-7B-SFT-gguf-q4_k_m.gguf	Q4_K_M	4.37 GB
Tess-3-7B-SFT-gguf-q4_k_s.gguf	Q4_K_S	4.14 GB
Tess-3-7B-SFT-gguf-iq4_xs.gguf	IQ4_XS	3.95 GB
Tess-3-7B-SFT-gguf-q3_k_l.gguf	Q3_K_L	3.83 GB
Tess-3-7B-SFT-gguf-q3_k_m.gguf	Q3_K_M	3.52 GB
Tess-3-7B-SFT-gguf-iq3_m.gguf	IQ3_M	3.29 GB
Tess-3-7B-SFT-gguf-q3_k_s.gguf	Q3_K_S	3.17 GB
Tess-3-7B-SFT-gguf-iq3_xs.gguf	IQ3_XS	3.02 GB
Tess-3-7B-SFT-gguf-q2_k.gguf	Q2_K	2.72 GB
Tess-3-7B-SFT-gguf-iq3_xxs.gguf	IQ3_XXS	136 MB
Tess-3-7B-SFT-gguf-iq2_m.gguf	IQ2_M	83.7 MB

Downloading using huggingface-cli

pip install -U "huggingface_hub[cli]"
huggingface-cli download juvi21/Tess-3-7B-SFT-GGUF --include "Tess-3-7B-SFT-gguf-q4_k_m.gguf" --local-dir ./

Downloads last month: 92

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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

Model tree for juvi21/Tess-3-7B-SFT-GGUF

Base model

mistralai/Mistral-7B-v0.3

Finetuned

migtissera/Tess-3-7B-SFT

Quantized

(5)

this model