Instructions to use mygitphase/guhan-m-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mygitphase/guhan-m-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mygitphase/guhan-m-gguf",
	filename="sarvam-m-bf16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mygitphase/guhan-m-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mygitphase/guhan-m-gguf:BF16
# Run inference directly in the terminal:
llama-cli -hf mygitphase/guhan-m-gguf:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mygitphase/guhan-m-gguf:BF16
# Run inference directly in the terminal:
llama-cli -hf mygitphase/guhan-m-gguf:BF16

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 mygitphase/guhan-m-gguf:BF16
# Run inference directly in the terminal:
./llama-cli -hf mygitphase/guhan-m-gguf:BF16

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 mygitphase/guhan-m-gguf:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mygitphase/guhan-m-gguf:BF16

Use Docker

docker model run hf.co/mygitphase/guhan-m-gguf:BF16

LM Studio
Jan
Ollama
How to use mygitphase/guhan-m-gguf with Ollama:
```
ollama run hf.co/mygitphase/guhan-m-gguf:BF16
```

Unsloth Studio new

How to use mygitphase/guhan-m-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 mygitphase/guhan-m-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 mygitphase/guhan-m-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mygitphase/guhan-m-gguf to start chatting

Docker Model Runner
How to use mygitphase/guhan-m-gguf with Docker Model Runner:
```
docker model run hf.co/mygitphase/guhan-m-gguf:BF16
```

Lemonade

How to use mygitphase/guhan-m-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mygitphase/guhan-m-gguf:BF16

Run and chat with the model

lemonade run user.guhan-m-gguf-BF16

List all available models

lemonade list

Sarvam-M

Model Information

This repository contains gguf version of sarvam-m in bf16 precision.

Learn more about sarvam-m in our detailed blog post.

Running the model on a CPU

You can use the model on your local machine (without gpu) as explained here.

Example Command:

./build/bin/llama-cli -i -m /your/folder/path/sarvam-m-bf16.gguf -c 8192 -t 16

Downloads last month: 179

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

16-bit

Inference Providers NEW

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

Model tree for mygitphase/guhan-m-gguf

Base model

mistralai/Mistral-Small-3.1-24B-Base-2503

Finetuned

sarvamai/sarvam-m

Quantized

(22)

this model