> ## Documentation Index
> Fetch the complete documentation index at: https://docs.liquid.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# LFM2.5-230M
> Ultra-compact 230M parameter model for data extraction and lightweight on-device agentic tasks
export const TextLlamacpp = ({ggufRepo, samplingFlags}) =>
Install:
{`brew install llama.cpp`}
Run:
{`llama-cli -hf ${ggufRepo} -c 4096 --color -i \\
${samplingFlags}`}
The -hf flag downloads the model directly from Hugging Face. For other installation methods and advanced usage, see the llama.cpp guide.
;
export const TextSglang = ({modelId, toolCallParser, samplingParams}) =>
Install:
{`uv pip install "sglang>=0.5.10"`}
Launch server:
{toolCallParser ? `sglang serve \\
--model-path ${modelId} \\
--host 0.0.0.0 \\
--port 30000 \\
--tool-call-parser ${toolCallParser}` : `sglang serve \\
--model-path ${modelId} \\
--host 0.0.0.0 \\
--port 30000`}
Query (OpenAI-compatible):
{`from openai import OpenAI
client = OpenAI(base_url="http://localhost:30000/v1", api_key="None")
response = client.chat.completions.create(
model="${modelId}",
messages=[{"role": "user", "content": "What is machine learning?"}],
${samplingParams || "temperature=0.3,"}
)
print(response.choices[0].message.content)`}
;
export const TextVllm = ({modelId, samplingParams, maxTokens}) =>
Install:
{`pip install vllm==0.14`}
Run:
{`from vllm import LLM, SamplingParams
llm = LLM(model="${modelId}")
sampling_params = SamplingParams(${samplingParams}max_tokens=${maxTokens || 512})
output = llm.chat("What is machine learning?", sampling_params)
print(output[0].outputs[0].text)`}
;
export const TextTransformers = ({modelId, samplingParams}) =>
Install:
{`pip install "transformers>=5.2.0" torch accelerate`}
Download & Run:
{`from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "${modelId}"
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="auto",
dtype="bfloat16",
)
tokenizer = AutoTokenizer.from_pretrained(model_id)
inputs = tokenizer.apply_chat_template(
[{"role": "user", "content": "What is machine learning?"}],
add_generation_prompt=True,
return_tensors="pt",
tokenize=True,
return_dict=True,
).to(model.device)
output = model.generate(**inputs, ${samplingParams}max_new_tokens=512)
input_length = inputs["input_ids"].shape[1]
response = tokenizer.decode(output[0][input_length:], skip_special_tokens=True)
print(response)`}
;
← Back to Text Models
LFM2.5-230M is Liquid AI's smallest LFM2.5 text model, designed for edge devices with the tightest memory and compute budgets. Built on the LFM2.5 architecture, it is tuned for data extraction and lightweight on-device agentic tasks such as tool calling. It is not recommended for reasoning-heavy workloads like advanced math, code generation, or creative writing — use [LFM2.5-350M](/lfm/models/lfm25-350m) or a larger model for those.
## Specifications
| Property | Value |
| -------------- | -------------- |
| Parameters | 230M |
| Context Length | 32K tokens |
| Architecture | LFM2.5 (Dense) |
Smallest LFM2.5 footprint for the tightest memory budgets
Powers large-scale extraction pipelines
Fast on-device agentic tasks and tool calling
## Quick Start