Instructions to use xocialize/LFM2.5-8B-A1B-MLX-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xocialize/LFM2.5-8B-A1B-MLX-6bit 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("xocialize/LFM2.5-8B-A1B-MLX-6bit")

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 xocialize/LFM2.5-8B-A1B-MLX-6bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "xocialize/LFM2.5-8B-A1B-MLX-6bit"

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": "xocialize/LFM2.5-8B-A1B-MLX-6bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use xocialize/LFM2.5-8B-A1B-MLX-6bit 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 "xocialize/LFM2.5-8B-A1B-MLX-6bit"

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 xocialize/LFM2.5-8B-A1B-MLX-6bit

Run Hermes

hermes

OpenClaw new

How to use xocialize/LFM2.5-8B-A1B-MLX-6bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "xocialize/LFM2.5-8B-A1B-MLX-6bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "xocialize/LFM2.5-8B-A1B-MLX-6bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use xocialize/LFM2.5-8B-A1B-MLX-6bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "xocialize/LFM2.5-8B-A1B-MLX-6bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "xocialize/LFM2.5-8B-A1B-MLX-6bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "xocialize/LFM2.5-8B-A1B-MLX-6bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

LFM2.5-8B-A1B-MLX-6bit — availability mirror

A verbatim mirror of LiquidAI/LFM2.5-8B-A1B-MLX-6bit. 6-bit quantized.

Why this repo exists

We ship Swift/MLX packages that name a weight repo in code. When an upstream repo moves or disappears, every already-published version of those packages breaks for anyone installing fresh — there is no redirect and no way to patch software already in someone's hands.

That is not hypothetical: an unrelated model family we had ported was reorganized onto a new HuggingFace org without redirects, and six of our published packages broke the same day. This mirror exists so that the same failure cannot take LFM2.5 with it.

It exists for durability, not improvement. Nothing here is changed, tuned, or repackaged, and LiquidAI's original is the better place to get these weights if you want the newest revision. All model IP, training, and quantization are LiquidAI's work.

Integrity

Byte-for-byte identical to upstream. Every file was verified by SHA-256 against the corresponding LiquidAI/LFM2.5-8B-A1B-MLX-6bit file immediately before upload, and the published copies were re-verified afterward. The hashes are listed below so the claim is checkable rather than merely asserted:

25e731c697c4fe4c52ee654cedf7106a827748d2  LICENSE
0a6d65da17453c1877163d0e426d5c4b58ba9c35  README.md
8bca4a545e9ec8dc0c5d4689a78886c0741c47e4  chat_template.jinja
4aed9e24101d6ad644dbd4f679c251cff7a2fd59  config.json
d14c980b6f1908b204b4b448734a0a508624960a  generation_config.json
a88e1d21cfa853bc1b33f82b73af36ab0d5a6f6ee15646e861234e40e96db6af  model-00001-of-00002.safetensors
d8e1c9d78a43e7349e55e8cf00cd30b8e2506115db0d58dc9994ae4e38d4af76  model-00002-of-00002.safetensors
b70de07d307393de2a6b5ef761e8222b508f10bc  model.safetensors.index.json
695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41  tokenizer.json
df190b8c97179c7b2fde48758a353b1bcfb18c83  tokenizer_config.json

Small non-LFS files (configs, tokenizer metadata) carry no upstream hash to compare against and were verified by exact byte size.

Licence — the commercial threshold matters

These weights are governed by the LFM Open License v1.0, included in full as LICENSE. Mirroring changes nothing about it.

It is Apache-2.0-shaped, with one condition that is easy to miss and important if you are building a product rather than experimenting:

Section 5 — Commercial Use limitation. Commercial use by a legal entity with annual revenue at or above $10,000,000 USD is not licensed under this agreement. Below that threshold, commercial use is permitted. Qualified non-profits are exempt for non-commercial and research purposes.

Redistribution is expressly permitted by §4, on four conditions: supply a copy of the licence, mark any files you modified, retain attribution notices, and carry forward any NOTICE file. We have modified nothing.

This summary is a pointer, not a substitute for reading the licence, and where the two differ the licence governs.

Credit

LFM2.5-8B-A1B is designed, trained, quantized, and released by LiquidAI. This mirror adds nothing but an address we can promise not to move.

Downloads last month: 14

Safetensors

Model size

8B params

Tensor type

BF16

U32

F32

MLX

Hardware compatibility

6-bit

Model tree for xocialize/LFM2.5-8B-A1B-MLX-6bit

Base model

LiquidAI/LFM2.5-8B-A1B-Base

Finetuned

LiquidAI/LFM2.5-8B-A1B

Quantized

(63)

this model