Instructions to use LiquidAI/LFM2.5-1.2B-JP-MLX-5bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/LFM2.5-1.2B-JP-MLX-5bit 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("LiquidAI/LFM2.5-1.2B-JP-MLX-5bit")

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 LiquidAI/LFM2.5-1.2B-JP-MLX-5bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "LiquidAI/LFM2.5-1.2B-JP-MLX-5bit"

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": "LiquidAI/LFM2.5-1.2B-JP-MLX-5bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use LiquidAI/LFM2.5-1.2B-JP-MLX-5bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "LiquidAI/LFM2.5-1.2B-JP-MLX-5bit"

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 "LiquidAI/LFM2.5-1.2B-JP-MLX-5bit" \
  --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 LiquidAI/LFM2.5-1.2B-JP-MLX-5bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "LiquidAI/LFM2.5-1.2B-JP-MLX-5bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "LiquidAI/LFM2.5-1.2B-JP-MLX-5bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "LiquidAI/LFM2.5-1.2B-JP-MLX-5bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use LiquidAI/LFM2.5-1.2B-JP-MLX-5bit 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 "LiquidAI/LFM2.5-1.2B-JP-MLX-5bit"

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 LiquidAI/LFM2.5-1.2B-JP-MLX-5bit

Run Hermes

hermes

Try LFM • Documentation • LEAP

LFM2.5-1.2B-JP-5bit

MLX export of LFM2.5-1.2B-JP for Apple Silicon inference.

LFM2.5-JP is a Japanese language model based on the LFM2.5 hybrid architecture, optimized for Japanese text generation and completion tasks.

Model Details

Property	Value
Parameters	1.2B
Precision	5-bit
Group Size	64
Context Length	128K

Recommended Sampling Parameters

Parameter	Value
temperature	0.3
min_p	0.15
repetition_penalty	1.05
max_tokens	512

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate
from mlx_lm.sample_utils import make_sampler, make_logits_processors

model, tokenizer = load("LiquidAI/LFM2.5-1.2B-JP-5bit")

prompt = "東京は日本の"

sampler = make_sampler(temp=0.3, min_p=0.15)
logits_processors = make_logits_processors(repetition_penalty=1.05)

response = generate(
    model,
    tokenizer,
    prompt=prompt,
    max_tokens=512,
    sampler=sampler,
    logits_processors=logits_processors,
    verbose=True,
)

License

This model is released under the LFM 1.0 License.

Downloads last month: 81

Safetensors

Model size

0.2B params

Tensor type

BF16

U32

MLX

Hardware compatibility

5-bit

Model tree for LiquidAI/LFM2.5-1.2B-JP-MLX-5bit

Base model

LiquidAI/LFM2.5-1.2B-Base

Finetuned

LiquidAI/LFM2.5-1.2B-JP

Quantized

(26)

this model