Instructions to use mkurman/lfm2-350M-med with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mkurman/lfm2-350M-med with Transformers:

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

pipe = pipeline("text-generation", model="mkurman/lfm2-350M-med")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mkurman/lfm2-350M-med")
model = AutoModelForCausalLM.from_pretrained("mkurman/lfm2-350M-med")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use mkurman/lfm2-350M-med with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mkurman/lfm2-350M-med",
	filename="lfm2-350M-med-q8_0.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 mkurman/lfm2-350M-med with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mkurman/lfm2-350M-med:Q8_0
# Run inference directly in the terminal:
llama-cli -hf mkurman/lfm2-350M-med:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mkurman/lfm2-350M-med:Q8_0
# Run inference directly in the terminal:
llama-cli -hf mkurman/lfm2-350M-med:Q8_0

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 mkurman/lfm2-350M-med:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf mkurman/lfm2-350M-med:Q8_0

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 mkurman/lfm2-350M-med:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mkurman/lfm2-350M-med:Q8_0

Use Docker

docker model run hf.co/mkurman/lfm2-350M-med:Q8_0

LM Studio
Jan

vLLM

How to use mkurman/lfm2-350M-med with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mkurman/lfm2-350M-med"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mkurman/lfm2-350M-med",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mkurman/lfm2-350M-med:Q8_0

SGLang

How to use mkurman/lfm2-350M-med 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 "mkurman/lfm2-350M-med" \
    --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": "mkurman/lfm2-350M-med",
		"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 "mkurman/lfm2-350M-med" \
        --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": "mkurman/lfm2-350M-med",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use mkurman/lfm2-350M-med with Ollama:
```
ollama run hf.co/mkurman/lfm2-350M-med:Q8_0
```

Unsloth Studio new

How to use mkurman/lfm2-350M-med 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 mkurman/lfm2-350M-med 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 mkurman/lfm2-350M-med to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mkurman/lfm2-350M-med to start chatting

Pi new

How to use mkurman/lfm2-350M-med with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mkurman/lfm2-350M-med:Q8_0

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": "mkurman/lfm2-350M-med:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mkurman/lfm2-350M-med with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mkurman/lfm2-350M-med:Q8_0

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 mkurman/lfm2-350M-med:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use mkurman/lfm2-350M-med with Docker Model Runner:
```
docker model run hf.co/mkurman/lfm2-350M-med:Q8_0
```

Lemonade

How to use mkurman/lfm2-350M-med with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mkurman/lfm2-350M-med:Q8_0

Run and chat with the model

lemonade run user.lfm2-350M-med-Q8_0

List all available models

lemonade list

lfm2-350M-med

Small medical fine-tune on top of LiquidAI’s LFM2-350M.
This checkpoint specializes the 350M LFM2 base for medical Q&A and tool-augmented search, using a light-weight recipe designed for laptops/edge boxes.

⚠️ Medical safety: This model is not a clinician. It may hallucinate and should not be used for diagnosis or treatment. Always seek qualified medical supervision.

TL;DR

Base: LiquidAI/LFM2-350M.
Training:
1. SFT on open-source medical data + tool-calling (search) traces
2. DPO preference alignment using MedMCQA as a preference signal
3. Post-merge with the base via Arcee Fusion (MergeKit) for controlled weight fusion
Eval (author’s harness)
- MMLU-Pro: 19.46 (vs 18.76 base in same harness)
- IFEVAL: 52.595 (vs 61.72 base in same harness)
  Note: LFM2’s official IFEVAL uses a different internal harness and reports ~65 on IFEVAL for the base; numbers are not directly comparable across harnesses.

What’s inside

Base model: LFM2-350M

Designed for on-device inference, with strong CPU latency and a ChatML-like template.
Supports tool use with dedicated special tokens (<tool_call>, </tool_call>, etc.).
See the base card for the full template and examples.

Specialization steps

Domain SFT (medical + tools)
- Instruction-style Q&A from open medical sources and synthetic conversions.
- Tool-use (search) supervised traces to teach function calling patterns.
Preference alignment (DPO)
- Direct Preference Optimization with MedMCQA-derived preferences to bias toward clinically reasonable short answers.
- Rationale: DPO is simple, stable at a small scale, and works well for short-form medical responses.
Model fusion (Arcee Fusion)
- Final merge uses Arcee Fusion in MergeKit, which selectively fuses parameters to avoid over-averaging and can be configured via merge_method: arcee_fusion.

Intended use & limitations

Use: education, research.
Don’t use: any medical advice.

Evaluation

All results below were run with the author’s harness; they will differ from LiquidAI’s internal suite and Open LLM Leaderboard settings.

Benchmark	lfm2-350M-med	LFM2-350M (same harness)
MMLU-Pro	19.46	18.76
IFEVAL	52.595	61.72

MMLU-Pro raises difficulty with 10 choices and more reasoning-heavy items—small models typically drop vs standard MMLU, so small absolute movements are meaningful.
IFEVAL measures verifiable instruction-following; scores depend heavily on prompt templates and verification scripts.

Quickstart (Transformers)

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "mkurman/lfm2-350M-med"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16")

messages = [
  {"role": "system", "content": "You are a careful medical assistant. Cite sources and warn that outputs are not medical advice."},
  {"role": "user", "content": "Briefly explain the difference between cellulitis and erysipelas."}
]

prompt = tok.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
out = model.generate(**tok(prompt, return_tensors="pt"), max_new_tokens=256)
print(tok.decode(out[0], skip_special_tokens=True))

Downloads last month: 50

Safetensors

Model size

0.4B params

Tensor type

F32

Model tree for mkurman/lfm2-350M-med

Base model

LiquidAI/LFM2-350M

Quantized

(33)

this model