Instructions to use mradermacher/medgemma-4b-pt-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/medgemma-4b-pt-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/medgemma-4b-pt-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/medgemma-4b-pt-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 mradermacher/medgemma-4b-pt-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/medgemma-4b-pt-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 mradermacher/medgemma-4b-pt-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/medgemma-4b-pt-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 mradermacher/medgemma-4b-pt-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/medgemma-4b-pt-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 mradermacher/medgemma-4b-pt-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/medgemma-4b-pt-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/medgemma-4b-pt-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/medgemma-4b-pt-GGUF with Ollama:
```
ollama run hf.co/mradermacher/medgemma-4b-pt-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/medgemma-4b-pt-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 mradermacher/medgemma-4b-pt-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 mradermacher/medgemma-4b-pt-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/medgemma-4b-pt-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use mradermacher/medgemma-4b-pt-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/medgemma-4b-pt-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/medgemma-4b-pt-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/medgemma-4b-pt-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.medgemma-4b-pt-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on May 24, 2025

Commit

1e4f694

verified ·

1 Parent(s): 8209168

uploaded from nico1

Browse files

Files changed (13) hide show

.gitattributes +12 -0
medgemma-4b-pt.IQ4_XS.gguf +3 -0
medgemma-4b-pt.Q2_K.gguf +3 -0
medgemma-4b-pt.Q3_K_L.gguf +3 -0
medgemma-4b-pt.Q3_K_M.gguf +3 -0
medgemma-4b-pt.Q3_K_S.gguf +3 -0
medgemma-4b-pt.Q4_K_M.gguf +3 -0
medgemma-4b-pt.Q4_K_S.gguf +3 -0
medgemma-4b-pt.Q5_K_M.gguf +3 -0
medgemma-4b-pt.Q5_K_S.gguf +3 -0
medgemma-4b-pt.Q6_K.gguf +3 -0
medgemma-4b-pt.Q8_0.gguf +3 -0
medgemma-4b-pt.f16.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -35,3 +35,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 medgemma-4b-pt.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 medgemma-4b-pt.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 medgemma-4b-pt.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 medgemma-4b-pt.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text
+medgemma-4b-pt.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+medgemma-4b-pt.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+medgemma-4b-pt.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+medgemma-4b-pt.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+medgemma-4b-pt.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+medgemma-4b-pt.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+medgemma-4b-pt.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+medgemma-4b-pt.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+medgemma-4b-pt.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+medgemma-4b-pt.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+medgemma-4b-pt.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+medgemma-4b-pt.f16.gguf filter=lfs diff=lfs merge=lfs -text

medgemma-4b-pt.IQ4_XS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:addf041707328500fcb28f772648b8c99d504495228248b4b63df4ac790789be
+size 2279624992

medgemma-4b-pt.Q2_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b40e84438b28985358708baf415a0c2a7cd66d77bf2fcf973d6874be92c38d1d
+size 1729163552

medgemma-4b-pt.Q3_K_L.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:37219121ee0e52d30a4c538e3decf3af24bdf48d547ac64e89ccfb17ab7f1fd5
+size 2236084512

medgemma-4b-pt.Q3_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e710c5803bd86114d9e12740bf1f22823b3a86cbd3ff781bc9164fef04348c16
+size 2098458912

medgemma-4b-pt.Q3_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f6bc241f3595b9570815eec14181fc5b516cb436822d1a7bb894646f55e4be9e
+size 1937363232

medgemma-4b-pt.Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:23f79cf61d2766c87f27cb8bdc5c2a96da13637ce754af8df52c87f98b47d6bc
+size 2489893152

medgemma-4b-pt.Q4_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:aa10735b371641c39067b0ca71de3d7184c6068635ebff163b1c1a7b47738ccc
+size 2377928992

medgemma-4b-pt.Q5_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:878c80f3ff73da6ca86a9705dd351d25c319678ecb05fc993df1f2157937af84
+size 2829697312

medgemma-4b-pt.Q5_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dac24a7c8cdb128734188a37e37939041516682cb052bd044ed5c92eec0fbe62
+size 2764591392

medgemma-4b-pt.Q6_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6654e34cedfb1cbfacd6c188e202fd4c8da17f17252b12da8e7e6c7a623e575a
+size 3190739232

medgemma-4b-pt.Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7209b1620a02ad9fc45c093b1f3638a08fd98dfde44745fcfdbc96cc8c38f3
+size 4130401312

medgemma-4b-pt.f16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a3b60573f06b68ba23d4362946d048db65e23588e035e4a14f14abe829a2a1c9
+size 7767802912