Instructions to use lmstudio-community/LFM2.5-2.6B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lmstudio-community/LFM2.5-2.6B-MLX-4bit 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("lmstudio-community/LFM2.5-2.6B-MLX-4bit")

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 lmstudio-community/LFM2.5-2.6B-MLX-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "lmstudio-community/LFM2.5-2.6B-MLX-4bit"

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": "lmstudio-community/LFM2.5-2.6B-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use lmstudio-community/LFM2.5-2.6B-MLX-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "lmstudio-community/LFM2.5-2.6B-MLX-4bit"

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 "lmstudio-community/LFM2.5-2.6B-MLX-4bit" \
  --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 lmstudio-community/LFM2.5-2.6B-MLX-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "lmstudio-community/LFM2.5-2.6B-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "lmstudio-community/LFM2.5-2.6B-MLX-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "lmstudio-community/LFM2.5-2.6B-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use lmstudio-community/LFM2.5-2.6B-MLX-4bit 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 "lmstudio-community/LFM2.5-2.6B-MLX-4bit"

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 lmstudio-community/LFM2.5-2.6B-MLX-4bit

Run Hermes

hermes

💫 Community Model> LFM2.5-2.6B by LiquidAI

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord.

Model creator: LiquidAI
Original model: LFM2.5-2.6B
Source revision: dca1825886789bd40b94368f53b1d9ada4c94598
MLX quantization: provided by LM Studio team using mlx_lm

Technical Details

4-bit affine quantized version of LFM2.5-2.6B using a group size of 64, optimized for Apple Silicon.

Conversion and modification notice

LM Studio converted the pinned source model from BF16 safetensors to MLX safetensors with mlx-lm 0.30.8 at commit 9c113f7. The weights were changed from the source in format and numerical precision.

The source config.json was changed to add MLX-LM-compatible aliases: block_ff_dim=10752 (matching intermediate_size) and top-level rope_theta=10000000.0 (matching rope_parameters.rope_theta). MLX-LM also added quantization metadata, and tokenizer_config.json was changed to embed the source chat template for compatibility. No other architecture or tokenizer behavior was intentionally changed.

Reasoning behavior

LFM2.5-2.6B is an always-thinking model. Its source chat template begins every assistant turn with <think>; there is no supported template switch to disable reasoning.

License

This model is distributed under the LFM Open License v1.0. Review the license before using or redistributing the model, including its commercial-use limitation.

Special thanks

🙏 Special thanks to the Apple Machine Learning Research team for creating MLX.

Disclaimers

LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Downloads last month: -

Safetensors

Model size

0.4B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for lmstudio-community/LFM2.5-2.6B-MLX-4bit

Base model

LiquidAI/LFM2.5-2.6B-Base

Finetuned

LiquidAI/LFM2.5-2.6B

Quantized

(40)

this model