Instructions to use OsaurusAI/LFM2.5-230M-MXFP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/LFM2.5-230M-MXFP8 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("OsaurusAI/LFM2.5-230M-MXFP8")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use OsaurusAI/LFM2.5-230M-MXFP8 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/LFM2.5-230M-MXFP8"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "OsaurusAI/LFM2.5-230M-MXFP8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use OsaurusAI/LFM2.5-230M-MXFP8 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/LFM2.5-230M-MXFP8"

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 OsaurusAI/LFM2.5-230M-MXFP8

Run Hermes

hermes

MLX LM

How to use OsaurusAI/LFM2.5-230M-MXFP8 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "OsaurusAI/LFM2.5-230M-MXFP8"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "OsaurusAI/LFM2.5-230M-MXFP8"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "OsaurusAI/LFM2.5-230M-MXFP8",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

LFM2.5-230M · MXFP8

Official OsaurusAI MXFP8 build of LiquidAI/LFM2.5-230M (LFM Open License v1.0) — Liquid AI's 230M tiny hybrid model. Near-lossless 8-bit microscaled FP; runs on Apple Silicon via Osaurus / mlx_lm.

~231 MB bundle (down from ~459 MB bf16) — small enough for the most constrained on-device use.
MXFP8: microscaled FP8 (group-size 32) on the linear weights; short-conv kernels and norms kept fp16.
Text-only, multilingual (en, ar, zh, fr, de, ja, ko, es).

Architecture


Family	`lfm2` (hybrid)
Layers	14 — 8 short-conv (LIV) + 6 full-attention
Hidden	1024 · vocab 65536 · tied embeddings
Cache	hybrid (conv state + KV for attention layers)
Tools	Liquid Python-call format (`lfm2` tool parser)

The short-conv (LIV) layers (conv.conv kernel + conv.in_proj/conv.out_proj) interleave with full-attention layers — verified coherent generation in mlx_lm after quantization.

Usage

python -m mlx_lm generate --model OsaurusAI/LFM2.5-230M-MXFP8 --prompt "What is the capital of France?"

Or load in Osaurus for a local, no-setup agent loop.

Provenance

Base: LiquidAI/LFM2.5-230M © Liquid AI — LFM Open License v1.0 (see LICENSE)
Quantization: Osaurus · MXFP8 (microscaled FP8, group-size 32) · eric@osaurus.ai

Downloads last month: 43

Safetensors

Model size

64.6M params

Tensor type

U32

F16

MLX

Hardware compatibility

Quantized

Model tree for OsaurusAI/LFM2.5-230M-MXFP8

Base model

LiquidAI/LFM2.5-230M-Base

Finetuned

LiquidAI/LFM2.5-230M

Finetuned

(8)

this model