Instructions to use stanfordmimi/MedVAL-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stanfordmimi/MedVAL-4B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="stanfordmimi/MedVAL-4B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("stanfordmimi/MedVAL-4B-GGUF", dtype="auto")

llama-cpp-python

How to use stanfordmimi/MedVAL-4B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="stanfordmimi/MedVAL-4B-GGUF",
	filename="MedVAL-4B.IQ4_XS.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 stanfordmimi/MedVAL-4B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf stanfordmimi/MedVAL-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf stanfordmimi/MedVAL-4B-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 stanfordmimi/MedVAL-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf stanfordmimi/MedVAL-4B-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 stanfordmimi/MedVAL-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf stanfordmimi/MedVAL-4B-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 stanfordmimi/MedVAL-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf stanfordmimi/MedVAL-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/stanfordmimi/MedVAL-4B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use stanfordmimi/MedVAL-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stanfordmimi/MedVAL-4B-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": "stanfordmimi/MedVAL-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stanfordmimi/MedVAL-4B-GGUF:Q4_K_M

SGLang

How to use stanfordmimi/MedVAL-4B-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 "stanfordmimi/MedVAL-4B-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": "stanfordmimi/MedVAL-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "stanfordmimi/MedVAL-4B-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": "stanfordmimi/MedVAL-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use stanfordmimi/MedVAL-4B-GGUF with Ollama:
```
ollama run hf.co/stanfordmimi/MedVAL-4B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use stanfordmimi/MedVAL-4B-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 stanfordmimi/MedVAL-4B-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 stanfordmimi/MedVAL-4B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for stanfordmimi/MedVAL-4B-GGUF to start chatting

Pi new

How to use stanfordmimi/MedVAL-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf stanfordmimi/MedVAL-4B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "stanfordmimi/MedVAL-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use stanfordmimi/MedVAL-4B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf stanfordmimi/MedVAL-4B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default stanfordmimi/MedVAL-4B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use stanfordmimi/MedVAL-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/stanfordmimi/MedVAL-4B-GGUF:Q4_K_M
```

Lemonade

How to use stanfordmimi/MedVAL-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull stanfordmimi/MedVAL-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MedVAL-4B-GGUF-Q4_K_M

List all available models

lemonade list

asadaali commited on Jul 14, 2025

Commit

b039488

verified ·

1 Parent(s): 2d7719d

Uploaded model files

Browse files

Files changed (9) hide show

.gitattributes +8 -0
MedVAL-4B.IQ4_XS.gguf +3 -0
MedVAL-4B.Q2_K.gguf +3 -0
MedVAL-4B.Q3_K_L.gguf +3 -0
MedVAL-4B.Q3_K_M.gguf +3 -0
MedVAL-4B.Q3_K_S.gguf +3 -0
MedVAL-4B.Q4_K_M.gguf +3 -0
MedVAL-4B.Q4_K_S.gguf +3 -0
MedVAL-4B.Q5_K_M.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+MedVAL-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+MedVAL-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+MedVAL-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+MedVAL-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MedVAL-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MedVAL-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MedVAL-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MedVAL-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text

MedVAL-4B.IQ4_XS.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1a81fc886926c2a321d3899f2a44d6ccd682e03fc99e145e59d8d5d8557630
+size 2286316448

MedVAL-4B.Q2_K.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9817c9c7918b1b6aaf52c37eff0b6f8261fb100a59ca19e78928369ad33bda75
+size 1669499808

MedVAL-4B.Q3_K_L.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:69cffda6f7d818b1697b3594a041910ed674009946e3786bc40406a339cc9cf4
+size 2239785888

MedVAL-4B.Q3_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1e97b7bf363bbd29fd5a3e30274d824627c922282e7f01c832f4a3d4771120
+size 2075618208

MedVAL-4B.Q3_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0c25876fc36232f98318973fab2a863148accda16ec1e1df428f904c987526e6
+size 1886997408

MedVAL-4B.Q4_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cbcc14c6a6cff747e21c40f36f38ff1cdf69e81c19c2981da173f4a9f57d170c
+size 2497280928

MedVAL-4B.Q4_K_S.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:526b6e1542e1d28b728f0419ec5b267b04de3fc1993e3203a441f7cc7631bea0
+size 2383309728

MedVAL-4B.Q5_K_M.gguf ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:04f02b63d7f398ab4046eb47486c9679f515389e637941c00d4e2bc6048b0b6b
+size 2889513888