Instructions to use mkurman/LiquidAI-LFM2.5-350M-SYNTH with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mkurman/LiquidAI-LFM2.5-350M-SYNTH with Transformers:

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

pipe = pipeline("text-generation", model="mkurman/LiquidAI-LFM2.5-350M-SYNTH")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("mkurman/LiquidAI-LFM2.5-350M-SYNTH")
model = AutoModelForMultimodalLM.from_pretrained("mkurman/LiquidAI-LFM2.5-350M-SYNTH")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mkurman/LiquidAI-LFM2.5-350M-SYNTH with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mkurman/LiquidAI-LFM2.5-350M-SYNTH"
# 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/LiquidAI-LFM2.5-350M-SYNTH",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mkurman/LiquidAI-LFM2.5-350M-SYNTH

SGLang

How to use mkurman/LiquidAI-LFM2.5-350M-SYNTH 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/LiquidAI-LFM2.5-350M-SYNTH" \
    --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/LiquidAI-LFM2.5-350M-SYNTH",
		"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/LiquidAI-LFM2.5-350M-SYNTH" \
        --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/LiquidAI-LFM2.5-350M-SYNTH",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mkurman/LiquidAI-LFM2.5-350M-SYNTH with Docker Model Runner:
```
docker model run hf.co/mkurman/LiquidAI-LFM2.5-350M-SYNTH
```

LFM2.5-350M-SYNTH

A 350M-parameter reasoning model fine-tuned from LiquidAI/LFM2.5-350M on synthetic reasoning data. It produces explicit chain-of-thought (<think> … </think>) before answering, and is small enough to run on CPU or modest GPUs while retaining the base model's 128k context window.

Highlights

Reasoning-first: trained on SynthLabs-style traces for math, medical, and general reasoning.
Compact & fast: 350M params on the hybrid LFM2 architecture (convolution + sparse full-attention blocks), bf16.
Long context: inherits the base model's 128k max_position_embeddings.
Chat + tools: ChatML format with native tool-calling special tokens.

Model details

                │                                                  │          │         │        │
────────────────┼──────────────────────────────────────────────────┼──────────┼─────────┼────────┼────
Base model      │ LiquidAI/LFM2.5-350M                             │          │         │        │
Architecture    │ `Lfm2ForCausalLM` (hybrid conv / full-attention) │          │         │        │
Parameters      │ ~350M                                            │          │         │        │
Hidden size     │ 1024                                             │          │         │        │
Layers          │ 16 (12 conv + 4 full-attention)                  │          │         │        │
Attention heads │ 16 (8 KV heads, GQA)                             │          │         │        │
Vocab size      │ 65,536                                           │          │         │        │
Context length  │ 128,000                                          │          │         │        │
Precision       │ bfloat16                                         │          │         │        │
Chat format     │ ChatML (`<                                       │ im_start │ >` / `< │ im_end │ >`)

Training

Fully fine-tuned for 4,000 steps on a single A100:

Sequence length: 2,048
Effective batch size: 64
Optimizer: AdamW, LR 5e-5, warmup ratio 0.03
Precision: bf16

Datasets

PleIAs/SYNTH (https://huggingface.co/datasets/PleIAs/SYNTH)
mkurman/medical-reasoning-synthlabs-I (https://huggingface.co/datasets/mkurman/medical-reasoning-synthlabs-I)
mkurman/gsm8k-SynthLabs-reasoning (https://huggingface.co/datasets/mkurman/gsm8k-SynthLabs-reasoning)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "mkurman/LiquidAI-LFM2.5-350M-SYNTH"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto")

messages = [{"role": "user", "content": "Natalia sold 48 clips in April and half as many in May. How many in total?"}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)

out = model.generate(inputs, max_new_tokens=512, do_sample=True, temperature=0.6, top_p=0.95)
print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))

The model emits its reasoning inside … followed by the final answer.

Evaluation

TODO

Intended use & limitations

Research and experimentation with small reasoning models. As a 350M model trained largely on synthetic data, it can hallucinate and make reasoning errors. Not intended for medical, legal, or other high-stakes decisions - outputs must be independently verified.

License

Released under the LFM Open License (lfm1.0); see LICENSE (LICENSE).

Citation

@misc{kurman2025lfm25synth,
  title  = {LFM2.5-350M-SYNTH},
  author = {Kurman, Mariusz},
  year   = {2026},
  url    = {https://huggingface.co/mkurman/LiquidAI-LFM2.5-350M-SYNTH}
}

Downloads last month: 81

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for mkurman/LiquidAI-LFM2.5-350M-SYNTH

Base model

LiquidAI/LFM2.5-350M-Base

Finetuned

LiquidAI/LFM2.5-350M