Instructions to use tensorblock/unsloth_medgemma-27b-text-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/unsloth_medgemma-27b-text-it-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="tensorblock/unsloth_medgemma-27b-text-it-GGUF")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/unsloth_medgemma-27b-text-it-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/unsloth_medgemma-27b-text-it-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 tensorblock/unsloth_medgemma-27b-text-it-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/unsloth_medgemma-27b-text-it-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/unsloth_medgemma-27b-text-it-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/unsloth_medgemma-27b-text-it-GGUF:Q2_K

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 tensorblock/unsloth_medgemma-27b-text-it-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/unsloth_medgemma-27b-text-it-GGUF:Q2_K

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 tensorblock/unsloth_medgemma-27b-text-it-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/unsloth_medgemma-27b-text-it-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/unsloth_medgemma-27b-text-it-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/unsloth_medgemma-27b-text-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/unsloth_medgemma-27b-text-it-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": "tensorblock/unsloth_medgemma-27b-text-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/unsloth_medgemma-27b-text-it-GGUF:Q2_K

SGLang

How to use tensorblock/unsloth_medgemma-27b-text-it-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "tensorblock/unsloth_medgemma-27b-text-it-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/unsloth_medgemma-27b-text-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "tensorblock/unsloth_medgemma-27b-text-it-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/unsloth_medgemma-27b-text-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use tensorblock/unsloth_medgemma-27b-text-it-GGUF with Ollama:
```
ollama run hf.co/tensorblock/unsloth_medgemma-27b-text-it-GGUF:Q2_K
```
Unsloth Desktop
Docker Model Runner
How to use tensorblock/unsloth_medgemma-27b-text-it-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/unsloth_medgemma-27b-text-it-GGUF:Q2_K
```

Lemonade

How to use tensorblock/unsloth_medgemma-27b-text-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/unsloth_medgemma-27b-text-it-GGUF:Q2_K

Run and chat with the model

lemonade run user.unsloth_medgemma-27b-text-it-GGUF-Q2_K

List all available models

lemonade list

Atomic Chat

unsloth/medgemma-27b-text-it - GGUF

Join our Discord to learn more about what we're building ↗

This repo contains GGUF format model files for unsloth/medgemma-27b-text-it.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5753.

Our projects

Forge

An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio

A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

Prompt template

<bos><start_of_turn>user
{system_prompt}

{prompt}<end_of_turn>
<start_of_turn>model

Model file specification

Filename	Quant type	File Size	Description
medgemma-27b-text-it-Q2_K.gguf	Q2_K	10.503 GB	smallest, significant quality loss - not recommended for most purposes
medgemma-27b-text-it-Q3_K_S.gguf	Q3_K_S	12.167 GB	very small, high quality loss
medgemma-27b-text-it-Q3_K_M.gguf	Q3_K_M	13.437 GB	very small, high quality loss
medgemma-27b-text-it-Q3_K_L.gguf	Q3_K_L	14.543 GB	small, substantial quality loss
medgemma-27b-text-it-Q4_0.gguf	Q4_0	15.567 GB	legacy; small, very high quality loss - prefer using Q3_K_M
medgemma-27b-text-it-Q4_K_S.gguf	Q4_K_S	15.674 GB	small, greater quality loss
medgemma-27b-text-it-Q4_K_M.gguf	Q4_K_M	16.546 GB	medium, balanced quality - recommended
medgemma-27b-text-it-Q5_0.gguf	Q5_0	18.767 GB	legacy; medium, balanced quality - prefer using Q4_K_M
medgemma-27b-text-it-Q5_K_S.gguf	Q5_K_S	18.767 GB	large, low quality loss - recommended
medgemma-27b-text-it-Q5_K_M.gguf	Q5_K_M	19.271 GB	large, very low quality loss - recommended
medgemma-27b-text-it-Q6_K.gguf	Q6_K	22.167 GB	very large, extremely low quality loss
medgemma-27b-text-it-Q8_0.gguf	Q8_0	28.708 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/unsloth_medgemma-27b-text-it-GGUF --include "medgemma-27b-text-it-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/unsloth_medgemma-27b-text-it-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'

Downloads last month: 120

GGUF

Model size

27B params

Architecture

gemma3

Hardware compatibility

2-bit

3-bit

Model tree for tensorblock/unsloth_medgemma-27b-text-it-GGUF

Base model

google/gemma-3-27b-pt

Finetuned

google/medgemma-27b-text-it

Finetuned

unsloth/medgemma-27b-text-it

Quantized

(1)

this model