Instructions to use Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF",
	filename="sehatsaathi-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Ali-001-ch/sehatsaathi-gemma4-e4b-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 Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Ali-001-ch/sehatsaathi-gemma4-e4b-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 Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ali-001-ch/sehatsaathi-gemma4-e4b-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 Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF:Q4_K_M

Ollama
How to use Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF with Ollama:
```
ollama run hf.co/Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Ali-001-ch/sehatsaathi-gemma4-e4b-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 Ali-001-ch/sehatsaathi-gemma4-e4b-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 Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF to start chatting

Docker Model Runner
How to use Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF with Docker Model Runner:
```
docker model run hf.co/Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF:Q4_K_M
```

Lemonade

How to use Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.sehatsaathi-gemma4-e4b-GGUF-Q4_K_M

List all available models

lemonade list

SehatSaathi · صحت ساتھی · GGUF (Q4_K_M + Q8_0)

Quantized GGUF builds of the SehatSaathi LoRA fine-tune of Gemma 4 E4B, for offline phone & laptop deployment via Ollama or llama.cpp.

Source merged model: Ali-001-ch/sehatsaathi-gemma4-e4b
LoRA adapter only: Ali-001-ch/sehatsaathi-gemma4-e4b-lora
Base: unsloth/gemma-4-E4B-it

Files

File	Quant	Size	Use case
`sehatsaathi-q4_k_m.gguf`	Q4_K_M	~5.5 GB	Phones, edge devices
`sehatsaathi-q8_0.gguf`	Q8_0	~9 GB	Laptops, near-lossless

Quick start with Ollama

ollama pull hf.co/Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF:Q4_K_M
ollama run  hf.co/Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF:Q4_K_M

Quick start with llama.cpp

./llama-cli -m sehatsaathi-q4_k_m.gguf \
    --temp 1.0 --top-p 0.95 --top-k 64 --color --conversation

Disclaimer

SehatSaathi is a medical screening / triage assistant, NOT a substitute for a qualified doctor. In an emergency call 1122 (Pakistan Rescue). License: Apache-2.0 + Gemma Terms of Use.

Downloads last month: 360

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

4-bit

8-bit

Model tree for Ali-001-ch/sehatsaathi-gemma4-e4b-GGUF

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Finetuned

unsloth/gemma-4-E4B-it

Quantized

(11)

this model