Instructions to use Mungert/LFM2.5-1.2B-Thinking-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mungert/LFM2.5-1.2B-Thinking-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Mungert/LFM2.5-1.2B-Thinking-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Mungert/LFM2.5-1.2B-Thinking-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Mungert/LFM2.5-1.2B-Thinking-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Mungert/LFM2.5-1.2B-Thinking-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mungert/LFM2.5-1.2B-Thinking-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mungert/LFM2.5-1.2B-Thinking-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M

SGLang

How to use Mungert/LFM2.5-1.2B-Thinking-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Mungert/LFM2.5-1.2B-Thinking-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mungert/LFM2.5-1.2B-Thinking-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Mungert/LFM2.5-1.2B-Thinking-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mungert/LFM2.5-1.2B-Thinking-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Mungert/LFM2.5-1.2B-Thinking-GGUF with Ollama:
```
ollama run hf.co/Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M
```

Unsloth Studio

How to use Mungert/LFM2.5-1.2B-Thinking-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Mungert/LFM2.5-1.2B-Thinking-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Mungert/LFM2.5-1.2B-Thinking-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Mungert/LFM2.5-1.2B-Thinking-GGUF to start chatting

How to use Mungert/LFM2.5-1.2B-Thinking-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Mungert/LFM2.5-1.2B-Thinking-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M

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 "Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

Docker Model Runner
How to use Mungert/LFM2.5-1.2B-Thinking-GGUF with Docker Model Runner:
```
docker model run hf.co/Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M
```

Lemonade

How to use Mungert/LFM2.5-1.2B-Thinking-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LFM2.5-1.2B-Thinking-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Mungert/LFM2.5-1.2B-Thinking-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M

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 Mungert/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

Mungert commited on Feb 4

Commit

e1d7159

verified ·

1 Parent(s): 247752b

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +340 -0

README.md ADDED Viewed

	@@ -0,0 +1,340 @@

+---
+library_name: transformers
+license: other
+license_name: lfm1.0
+license_link: LICENSE
+language:
+- en
+- ar
+- zh
+- fr
+- de
+- ja
+- ko
+- es
+pipeline_tag: text-generation
+tags:
+- liquid
+- lfm2.5
+- edge
+base_model: LiquidAI/LFM2.5-1.2B-Base
+---
+# <span style="color: #7FFF7F;">LFM2.5-1.2B-Thinking GGUF Models</span>
+## <span style="color: #7F7FFF;">Model Generation Details</span>
+This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`0c21677e4`](https://github.com/ggerganov/llama.cpp/commit/0c21677e43044d27f6f7a7f9f95c67f7c4b3fdb4).
+---
+<a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;">
+  Click here to get info on choosing the right GGUF model format
+</a>
+---
+<!--Begin Original Model Card-->
+<div align="center">
+  <img
+    src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png"
+    alt="Liquid AI"
+    style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;"
+  />
+  <div style="display: flex; justify-content: center; gap: 0.5em; margin-bottom: 1em;">
+    <a href="https://playground.liquid.ai/"><strong>Try LFM</strong></a> •
+    <a href="https://docs.liquid.ai/lfm"><strong>Documentation</strong></a> •
+    <a href="https://leap.liquid.ai/"><strong>LEAP</strong></a>
+  </div>
+</div>
+# LFM2.5-1.2B-Thinking
+LFM2.5 is a new family of hybrid models designed for **on-device deployment**. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.
+- **Best-in-class performance**: A 1.2B model rivaling much larger models, bringing high-quality AI to your pocket.
+- **Fast edge inference**: 239 tok/s decode on AMD CPU, 82 tok/s on mobile NPU. Runs under 1GB of memory with day-one support for llama.cpp, MLX, and vLLM.
+- **Scaled training**: Extended pre-training from 10T to 28T tokens and large-scale multi-stage reinforcement learning.
+![LFM2.5-1.2B - Benchmarks-Light](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/KfNudLXnOZxAhlLp_1QVo.png)
+Find more information about LFM2.5-1.2B-Thinking in our [blog post](https://www.liquid.ai/blog/lfm2-5-1-2b-thinking-on-device-reasoning-under-1gb).
+## 🗒️ Model Details
+| Model | Parameters | Description |
+|-------|------------|-------------|
+| [LFM2.5-1.2B-Base](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Base) | 1.2B | Pre-trained base model for fine-tuning |
+| [LFM2.5-1.2B-Instruct](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct) | 1.2B | General-purpose instruction-tuned model |
+| [**LFM2.5-1.2B-Thinking**](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking) | 1.2B | General-purpose reasoning model |
+| [LFM2.5-1.2B-JP](https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP) | 1.2B | Japanese-optimized chat model |
+| [LFM2.5-VL-1.6B](https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B) | 1.6B | Vision-language model with fast inference |
+| [LFM2.5-Audio-1.5B](https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B) | 1.5B | Audio-language model for speech and text I/O |
+LFM2.5-1.2B-Thinking is a general-purpose text-only model with the following features:
+- **Number of parameters**: 1.17B
+- **Number of layers**: 16 (10 double-gated LIV convolution blocks + 6 GQA blocks)
+- **Training budget**: 28T tokens
+- **Context length**: 32,768 tokens
+- **Vocabulary size**: 65,536
+- **Knowledge cutoff**: Mid-2024
+- **Languages**: English, Arabic, Chinese, French, German, Japanese, Korean, Spanish
+- **Generation parameters**:
+  - `temperature: 0.05`
+  - `top_k: 50`
+  - `repetition_penalty: 1.05`
+| Model | Description |
+|-------|-------------|
+| [**LFM2.5-1.2B-Thinking**](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking) | Original model checkpoint in native format. Best for fine-tuning or inference with Transformers and vLLM. |
+| [LFM2.5-1.2B-Thinking-GGUF](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking-GGUF) | Quantized format for llama.cpp and compatible tools. Optimized for CPU inference and local deployment with reduced memory usage. |
+| [LFM2.5-1.2B-Thinking-ONNX](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking-ONNX) | ONNX Runtime format for cross-platform deployment. Enables hardware-accelerated inference across diverse environments (cloud, edge, mobile). |
+| [LFM2.5-1.2B-Thinking-MLX](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit) | MLX format for Apple Silicon. Optimized for fast inference on Mac devices using the MLX framework. |
+We recommend using it for agentic tasks, data extraction, and RAG. It is not recommended for knowledge-intensive tasks and programming.
+### Chat Template
+LFM2.5 uses a ChatML-like format. See the [Chat Template documentation](https://docs.liquid.ai/lfm/key-concepts/chat-template) for details. Example:
+```
+<|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
+```
+You can use [`tokenizer.apply_chat_template()`](https://huggingface.co/docs/transformers/en/chat_templating#using-applychattemplate) to format your messages automatically.
+### Tool Use
+LFM2.5 supports function calling as follows:
+1. **Function definition**: We recommend providing the list of tools as a JSON object in the system prompt. You can also use the [`tokenizer.apply_chat_template()`](https://huggingface.co/docs/transformers/en/chat_extras#passing-tools) function with tools.
+2. **Function call**: By default, LFM2.5 writes Pythonic function calls (a Python list between `<|tool_call_start|>` and `<|tool_call_end|>` special tokens), as the assistant answer. You can override this behavior by asking the model to output JSON function calls in the system prompt.
+3. **Function execution**: The function call is executed, and the result is returned as a "tool" role.
+4. **Final answer**: LFM2 interprets the outcome of the function call to address the original user prompt in plain text.
+See the [Tool Use documentation](https://docs.liquid.ai/lfm/key-concepts/tool-use) for the full guide. Example:
+```
+<|startoftext|><|im_start|>system
+List of tools: [{"name": "get_candidate_status", "description": "Retrieves the current status of a candidate in the recruitment process", "parameters": {"type": "object", "properties": {"candidate_id": {"type": "string", "description": "Unique identifier for the candidate"}}, "required": ["candidate_id"]}}]<|im_end|>
+<|im_start|>user
+What is the current status of candidate ID 12345?<|im_end|>
+<|im_start|>assistant
+<|tool_call_start|>[get_candidate_status(candidate_id="12345")]<|tool_call_end|>Checking the current status of candidate ID 12345.<|im_end|>
+<|im_start|>tool
+[{"candidate_id": "12345", "status": "Interview Scheduled", "position": "Clinical Research Associate", "date": "2023-11-20"}]<|im_end|>
+<|im_start|>assistant
+The candidate with ID 12345 is currently in the "Interview Scheduled" stage for the position of Clinical Research Associate, with an interview date set for 2023-11-20.<|im_end|>
+```
+## 🏃 Inference
+LFM2.5 is supported by many inference frameworks. See the [Inference documentation](https://docs.liquid.ai/lfm/inference/transformers) for the full list.
+| Name | Description | Docs | Notebook |
+|------|-------------|------|:--------:|
+| [Transformers](https://github.com/huggingface/transformers) | Simple inference with direct access to model internals. | <a href="https://docs.liquid.ai/lfm/inference/transformers">Link</a> | <a href="https://colab.research.google.com/drive/1_q3jQ6LtyiuPzFZv7Vw8xSfPU5FwkKZY?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
+| [vLLM](https://github.com/vllm-project/vllm) | High-throughput production deployments with GPU. | <a href="https://docs.liquid.ai/lfm/inference/vllm">Link</a> | <a href="https://colab.research.google.com/drive/1VfyscuHP8A3we_YpnzuabYJzr5ju0Mit?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
+| [llama.cpp](https://github.com/ggml-org/llama.cpp) | Cross-platform inference with CPU offloading. | <a href="https://docs.liquid.ai/lfm/inference/llama-cpp">Link</a> | <a href="https://colab.research.google.com/drive/1ohLl3w47OQZA4ELo46i5E4Z6oGWBAyo8?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
+| [MLX](https://github.com/ml-explore/mlx) | Apple's machine learning framework optimized for Apple Silicon. | <a href="https://docs.liquid.ai/lfm/inference/mlx">Link</a> | — |
+| [LM Studio](https://lmstudio.ai/) | Desktop application for running LLMs locally. | <a href="https://docs.liquid.ai/lfm/inference/lm-studio">Link</a> | — |
+Here's a quick start example with Transformers:
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+model_id = "LiquidAI/LFM2.5-1.2B-Thinking"
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    dtype="bfloat16",
+#   attn_implementation="flash_attention_2" <- uncomment on compatible GPU
+)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+prompt = "What is C. elegans?"
+input_ids = tokenizer.apply_chat_template(
+    [{"role": "user", "content": prompt}],
+    add_generation_prompt=True,
+    return_tensors="pt",
+    tokenize=True,
+).to(model.device)
+output = model.generate(
+    input_ids,
+    do_sample=True,
+    temperature=0.1,
+    top_k=50,
+    top_p=0.1,
+    repetition_penalty=1.05,
+    max_new_tokens=512,
+    streamer=streamer,
+)
+```
+## 🔧 Fine-Tuning
+We recommend fine-tuning LFM2.5 for your specific use case to achieve the best results.
+| Name | Description | Docs | Notebook |
+|------|-------------|------|----------|
+| CPT ([Unsloth](https://github.com/unslothai/unsloth)) | Continued Pre-Training using Unsloth for text completion. | <a href="https://docs.liquid.ai/lfm/fine-tuning/unsloth">Link</a> | <a href="https://colab.research.google.com/drive/10fm7eNMezs-DSn36mF7vAsNYlOsx9YZO?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
+| CPT ([Unsloth](https://github.com/unslothai/unsloth)) | Continued Pre-Training using Unsloth for translation. | <a href="https://docs.liquid.ai/lfm/fine-tuning/unsloth">Link</a> | <a href="https://colab.research.google.com/drive/1gaP8yTle2_v35Um8Gpu9239fqbU7UgY8?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
+| SFT ([Unsloth](https://github.com/unslothai/unsloth)) | Supervised Fine-Tuning with LoRA using Unsloth. | <a href="https://docs.liquid.ai/lfm/fine-tuning/unsloth">Link</a> | <a href="https://colab.research.google.com/drive/1vGRg4ksRj__6OLvXkHhvji_Pamv801Ss?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
+| SFT ([TRL](https://github.com/huggingface/trl)) | Supervised Fine-Tuning with LoRA using TRL. | <a href="https://docs.liquid.ai/lfm/fine-tuning/trl">Link</a> | <a href="https://colab.research.google.com/drive/1j5Hk_SyBb2soUsuhU0eIEA9GwLNRnElF?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
+| DPO ([TRL](https://github.com/huggingface/trl)) | Direct Preference Optimization with LoRA using TRL. | <a href="https://docs.liquid.ai/lfm/fine-tuning/trl">Link</a> | <a href="https://colab.research.google.com/drive/1MQdsPxFHeZweGsNx4RH7Ia8lG8PiGE1t?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
+| GRPO ([Unsloth](https://github.com/unslothai/unsloth)) | GRPO with LoRA using Unsloth. | <a href="https://docs.liquid.ai/lfm/fine-tuning/unsloth">Link</a> | <a href="https://colab.research.google.com/drive/1mIikXFaGvcW4vXOZXLbVTxfBRw_XsXa5?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
+| GRPO ([TRL](https://github.com/huggingface/trl)) | GRPO with LoRA using TRL. | <a href="https://docs.liquid.ai/lfm/fine-tuning/trl">Link</a> | <a href="https://colab.research.google.com/github/Liquid4All/cookbook/blob/main/finetuning/notebooks/grpo_for_verifiable_tasks.ipynb"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
+## 📊 Performance
+### Benchmarks
+We compared LFM2.5-1.2B-Thinking with relevant sub-2B models on a diverse suite of benchmarks.
+| Model                      | GPQA Diamond      | MMLU-Pro          | IFEval            | IFBench           | Multi-IF          | GSM8K             | MATH-500          | AIME25            | BFCLv3            |
+| -------------------------- | ----------------- | ----------------- | ----------------- | ----------------- | ----------------- | ----------------- | ----------------- | ----------------- | ----------------- |
+| **LFM2.5-1.2B-Thinking**   | 37.86<br>(± 0.83) | 49.65<br>(± 0.18) | 88.42<br>(± 0.35) | 44.85<br>(± 0.73) | 69.33<br>(± 0.09) | 85.60<br>(± 0.00) | 87.96<br>(± 0.72) | 31.73<br>(± 1.81) | 56.97<br>(± 0.30) |
+| Qwen3-1.7B (thinking mode) | 36.93<br>(± 2.07) | 56.68<br>(± 1.29) | 71.65<br>(± 0.13) | 25.88<br>(± 0.30) | 60.33<br>(± 0.02) | 85.60<br>(± 1.13) | 81.92<br>(± 2.99) | 36.27<br>(± 1.24) | 55.41<br>(± 0.04) |
+| LFM2.5-1.2B-Instruct       | 38.89             | 44.35             | 86.23             | 47.33             | 60.98             | 64.52             | 63.20             | 14.00             | 49.12             |
+| Qwen3-1.7B (instruct mode) | 34.85             | 42.91             | 73.68             | 21.33             | 56.48             | 33.66             | 70.40             | 9.33              | 46.30             |
+| Granite-4.0-H-1B           | 24.34             | 27.64             | 80.08             | 24.93             | 47.56             | 69.60             | 47.20             | 1                 | 50.69             |
+| Granite-4.0-1B             | 24.24             | 33.53             | 79.61             | 21                | 43.65             | 73.42             | 44.80             | 3.33              | 52.43             |
+| Gemma 3 1B IT              | 24.24             | 14.04             | 63.25             | 20.47             | 44.31             | 42.15             | 45.20             | 1                 | 16.64             |
+| Llama 3.2 1B Instruct      | 16.57             | 20.80             | 52.37             | 15.93             | 30.16             | 39.04             | 23.40             | 0.33              | 21.44             |
+GPQA, MMLU-Pro, IFBench, and AIME25 follow [ArtificialAnalysis's methodology](https://artificialanalysis.ai/methodology/intelligence-benchmarking). For IFEval and Multi-IF, we report the average score across strict and loose prompt and instruction accuracies. For BFCLv3, we report the final weighted average score with a custom Liquid handler to support our tool use template.
+Based on the same methodology, we report the average score and standard deviation across five runs with `temperature=0.6` for thinking models. For instruct models, we report scores using greedy decoding.
+### Response length
+In comparison with Qwen3-1.7B (thinking mode), it requires fewer output tokens while offering higher overall performance.
+![LFM2.5-1.2B - Average Response Length](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/Gcq_HUYLVC779xOuut2EI.png)
+### Inference speed
+LFM2.5-1.2B-Thinking offers extremely fast inference speed on CPUs with a low memory profile compared to similar-sized models.
+![LFM2.5-1.2B - Inference Performance](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/4ODY8nGws22vICfcMTxNx.png)
+In addition, we are partnering with AMD, Qualcomm, Nexa AI, and FastFlowLM to bring the LFM2.5 family to NPUs. These optimized models are available through our partners, enabling highly efficient on-device inference.
+We report the following numbers with 1K prefill and 100 decode tokens:
+| Device                                               | Inference | Framework        | Model                | Prefill (tok/s) | Decode (tok/s) | Memory |
+| ---------------------------------------------------- | --------- | ---------------- | -------------------- | --------------- | -------------- | ------ |
+| AMD Ryzen AI 395+                                    | NPU       | FastFlowLM       | LFM2.5-1.2B-Thinking | 1487            | 60             | 1600MB (full context) |
+| AMD Ryzen AI 9 HX 370                                | NPU       | FastFlowLM       | LFM2.5-1.2B-Thinking | 1487            | 57             | 1600MB (full context) |
+| AMD Ryzen AI 9 HX 370                                | CPU       | llama.cpp (Q4_0) | LFM2.5-1.2B-Thinking | 2975            | 116            | 856MB  |
+| Qualcomm Snapdragon® X Elite                         | NPU       | NexaML           | LFM2.5-1.2B-Thinking | 2591            | 63             | 0.9GB  |
+| Qualcomm Snapdragon® Gen4 (ROG Phone9 Pro)           | NPU       | NexaML           | LFM2.5-1.2B-Thinking | 4391            | 82             | 0.9GB  |
+| Qualcomm Dragonwing IQ9 (IQ-9075) (IoT)              | NPU       | NexaML           | LFM2.5-1.2B-Thinking | 2143            | 53             | 0.9 GB |
+| Qualcomm Snapdragon® Gen4 (Samsung Galaxy S25 Ultra) | CPU       | llama.cpp (Q4_0) | LFM2.5-1.2B-Thinking | 335             | 70             | 719MB  |
+**LFM2.5-1.2B-Thinking excels at long-context inference.** For example, on AMD Ryzen™ NPUs with FastFlowLM, decoding throughput sustains ~52 tok/s at 16K context and ~46 tok/s even at the full 32K context, indicating robust long-context scalability. For more details on longer context benchmarks on AMD Ryzen™ NPUs with FastFlowLM, please review these [here](https://fastflowlm.com/docs/benchmarks/lfm2_results/).
+These capabilities unlock new deployment scenarios across various devices, including vehicles, mobile devices, laptops, IoT devices, and embedded systems.
+## Contact
+For enterprise solutions and edge deployment, contact [[email protected]](mailto:[email protected]).
+## Citation
+```bibtex
+@article{liquidAI2026thinking,
+  author = {Liquid AI},
+  title = {LFM2.5-1.2B-Thinking: On-Device Reasoning Under 1GB},
+  journal = {Liquid AI Blog},
+  year = {2026},
+  note = {www.liquid.ai/blog/lfm2-5-1-2b-thinking-on-device-reasoning-under-1gb},
+}
+```
+```bibtex
+@article{liquidai2025lfm2,
+  title={LFM2 Technical Report},
+  author={Liquid AI},
+  journal={arXiv preprint arXiv:2511.23404},
+  year={2025}
+}
+```
+<!--End Original Model Card-->
+---
+# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
+Help me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**:
+👉 [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme)
+The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder)
+💬 **How to test**:
+ Choose an **AI assistant type**:
+   - `TurboLLM` (GPT-4.1-mini)
+   - `HugLLM` (Hugginface Open-source models)
+   - `TestLLM` (Experimental CPU-only)
+### **What I’m Testing**
+I’m pushing the limits of **small open-source models for AI network monitoring**, specifically:
+- **Function calling** against live network services
+- **How small can a model go** while still handling:
+  - Automated **Nmap security scans**
+  - **Quantum-readiness checks**
+  - **Network Monitoring tasks**
+🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):
+- ✅ **Zero-configuration setup**
+- ⏳ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low.
+- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate!
+### **Other Assistants**
+🟢 **TurboLLM** – Uses **gpt-4.1-mini** :
+- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited.
+- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents**
+- **Real-time network diagnostics and monitoring**
+- **Security Audits**
+- **Penetration testing** (Nmap/Metasploit)
+🔵 **HugLLM** – Latest Open-source models:
+- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.
+### 💡 **Example commands you could test**:
+1. `"Give me info on my websites SSL certificate"`
+2. `"Check if my server is using quantum safe encyption for communication"`
+3. `"Run a comprehensive security audit on my server"`
+4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a [Quantum Network Monitor Agent](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. This is a very flexible and powerful feature. Use with caution!
+### Final Word
+I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.
+If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.
+I'm also open to job opportunities or sponsorship.
+Thank you! 😊