Instructions to use stamsam/LFM2.5-8B-A1B-oQ5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stamsam/LFM2.5-8B-A1B-oQ5 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("stamsam/LFM2.5-8B-A1B-oQ5")

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 stamsam/LFM2.5-8B-A1B-oQ5 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "stamsam/LFM2.5-8B-A1B-oQ5"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "stamsam/LFM2.5-8B-A1B-oQ5"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use stamsam/LFM2.5-8B-A1B-oQ5 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "stamsam/LFM2.5-8B-A1B-oQ5"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "stamsam/LFM2.5-8B-A1B-oQ5"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "stamsam/LFM2.5-8B-A1B-oQ5",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use stamsam/LFM2.5-8B-A1B-oQ5 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 "stamsam/LFM2.5-8B-A1B-oQ5"

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 stamsam/LFM2.5-8B-A1B-oQ5

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use stamsam/LFM2.5-8B-A1B-oQ5 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "stamsam/LFM2.5-8B-A1B-oQ5"

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 "stamsam/LFM2.5-8B-A1B-oQ5" \
  --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"

stamsam commited on May 29

Commit

024de4d

verified ·

1 Parent(s): 6b7c3fd

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +63 -1

README.md CHANGED Viewed

@@ -1,14 +1,21 @@
 ---
 library_name: mlx
 tags:
 - mlx
 - oq
 - quantized
 ---
 # LFM2.5-8B-A1B-oQ5
-This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.3.12) mixed-precision quantization.
 ## Quantization details
@@ -16,3 +23,58 @@ This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.3.1
 - **Bits**: 5
 - **Group size**: 64
 - **Format**: MLX safetensors

 ---
 library_name: mlx
+license: other
+license_name: lfm1.0
+license_link: https://huggingface.co/LiquidAI/LFM2.5-8B-A1B/blob/main/LICENSE
 tags:
 - mlx
 - oq
 - quantized
+- lfm2.5
+- edge
+pipeline_tag: text-generation
+base_model: LiquidAI/LFM2.5-8B-A1B
 ---
 # LFM2.5-8B-A1B-oQ5
+This model is an **MLX oQ5 quantized** version of [LiquidAI/LFM2.5-8B-A1B](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B), quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.3.12) mixed-precision quantization.
 ## Quantization details
 - **Bits**: 5
 - **Group size**: 64
 - **Format**: MLX safetensors
+## Base Model: LFM2.5-8B-A1B
+LFM2.5 is a new family of hybrid models designed for on-device deployment by Liquid AI. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.
+### Model Details
+| Property | Value |
+| --- | --- |
+| Total parameters | 8.3B |
+| Active parameters | 1.5B |
+| Number of layers | 24 (18 double-gated LIV conv + 6 GQA) |
+| Training budget | 38 trillion tokens |
+| Context length | 131,072 |
+| Vocabulary size | 128,000 |
+| Languages | English, Arabic, Chinese, French, German, Japanese, Korean, Portuguese, Spanish |
+### Recommended Generation Parameters
+- `temperature: 0.2`
+- `top_p: 80`
+- `repetition_penalty: 1.05`
+### Chat Template
+LFM2.5 uses a ChatML-like format:
+```
+<|startoftext|><|im_start|>system
+You are a helpful assistant trained by Liquid AI.<|im_end|>
+<|im_start|>user
+What is C. elegans?<|im_end|>
+<|im_start|>assistant
+```
+### Citation
+```bibtex
+@article{liquidAI20268BA1B,
+  author  = {Liquid AI},
+  title   = {LFM2.5-8B-A1B: Personal Assistant On Your Laptop},
+  journal = {Liquid AI Blog},
+  year    = {2026},
+  note    = {www.liquid.ai/blog/lfm2-5-8b-a1b},
+}
+```
+```bibtex
+@article{liquidai2025lfm2,
+  title   = {LFM2 Technical Report},
+  author  = {Liquid AI},
+  journal = {arXiv preprint arXiv:2511.23404},
+  year    = {2025}
+}
+```