Instructions to use mohommed/LFM3-1.7B-Frontier-SmartAgent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mohommed/LFM3-1.7B-Frontier-SmartAgent with Transformers:

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

pipe = pipeline("text-generation", model="mohommed/LFM3-1.7B-Frontier-SmartAgent", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("mohommed/LFM3-1.7B-Frontier-SmartAgent", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mohommed/LFM3-1.7B-Frontier-SmartAgent 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 mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M

Use Docker

docker model run hf.co/mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use mohommed/LFM3-1.7B-Frontier-SmartAgent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mohommed/LFM3-1.7B-Frontier-SmartAgent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mohommed/LFM3-1.7B-Frontier-SmartAgent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M

SGLang

How to use mohommed/LFM3-1.7B-Frontier-SmartAgent 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 "mohommed/LFM3-1.7B-Frontier-SmartAgent" \
    --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": "mohommed/LFM3-1.7B-Frontier-SmartAgent",
		"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 "mohommed/LFM3-1.7B-Frontier-SmartAgent" \
        --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": "mohommed/LFM3-1.7B-Frontier-SmartAgent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use mohommed/LFM3-1.7B-Frontier-SmartAgent with Ollama:
```
ollama run hf.co/mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M
```
Unsloth Desktop

How to use mohommed/LFM3-1.7B-Frontier-SmartAgent with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use mohommed/LFM3-1.7B-Frontier-SmartAgent with Docker Model Runner:
```
docker model run hf.co/mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M
```

Lemonade

How to use mohommed/LFM3-1.7B-Frontier-SmartAgent with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M

Run and chat with the model

lemonade run user.LFM3-1.7B-Frontier-SmartAgent-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use mohommed/LFM3-1.7B-Frontier-SmartAgent with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mohommed/LFM3-1.7B-Frontier-SmartAgent: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 mohommed/LFM3-1.7B-Frontier-SmartAgent:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mohommed/LFM3-1.7B-Frontier-SmartAgent with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mohommed/LFM3-1.7B-Frontier-SmartAgent: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 "mohommed/LFM3-1.7B-Frontier-SmartAgent: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"

🚀 LFM3-1.7B-Frontier-SmartAgent (512K Context • 4-Stage Reasoning • Second Brain Agent)

LFM3-1.7B-Frontier-SmartAgent is an autonomous reasoning, coding, and tool-calling language model built on top of LiquidAI/LFM3-1.7B. It combines Liquid AI's 24-layer Tri-Hybrid architecture (Gated Short Convolutions + Sliding-Window Attention + Global Grouped-Query Attention) with 512K NTK-YaRN context scaling, Gram-Schmidt Damped Mid-Layer Orthogonalization, and a Two-Stage Post-Training Pipeline (Multi-Turn SFT + Multi-Objective GRPO).

Designed specifically for on-device and edge agentic systems, this model natively reasons through a structured 4-Stage Frontier Thinking Protocol (<think>...</think>), audits external context (<context>) and persistent associative memory (<second_brain>), and emits verified executable Python tool calls (<tool_call>...</tool_call>).

✨ Key Architectural Highlights

1. 🔭 512K (524,288 Token) NTK-Aware YaRN Context Scaling

Extended 2.0× from LFM3's native 262,144 context window to 524,288 tokens across both full and sliding-window attention layers using calibrated YaRN RoPE scaling (factor = 2.0, beta_fast = 32.0, beta_slow = 1.0, mscale = 1.14). This preserves high-frequency local positional resolution while enabling repository-scale AST dependency indexing.

2. 🧭 Gram-Schmidt Damped SVD Orthogonalization (Layers 9–19)

Rather than applying destructive full-model weight abliteration—which degrades small-model perplexity and state-space convolution stability—refusal directions are isolated via Singular Value Decomposition (SVD), orthogonalized against harmless technical reasoning activations via Gram-Schmidt projection, and subtracted exclusively from middle MLP down-projections (w2 / down_proj in layers 9–19) with a damping coefficient of $\alpha = 0.60$. Early shortconv feature extractors (layers 0–8) and final output calibration layers (layers 20–23) remain 100% untouched.

3. 🧠 Mandatory 4-Stage Frontier `<think>` Protocol

Unlike standard chat models whose chain-of-thought is unstructured or stripped during multi-turn conversations, LFM3-1.7B-Frontier-SmartAgent is trained with preserve_thinking = true to execute a strict 4-step cognitive audit before every action:

[1. CONTEXT & 2ND BRAIN AUDIT]: Inspects <context>, <second_brain>, and <tool_response> to separate verified facts from unknowns.
[2. DAG DECOMPOSITION]: Breaks complex goals into an ordered Directed Acyclic Graph (DAG) of atomic tool invocations.
[3. HALLUCINATION & CONSTRAINT CHECK]: Verifies every URL, file path, Set-of-Marks ID [#som_id], and function parameter signature against the active context.
[4. PRECISION EXECUTION]: Emits syntactically valid Python tool calls or a grounded final Markdown synthesis.

4. 🕸️ HippoRAG-2 Associative "Second Brain" & Multi-Hop Deep Research Ready

Trained to operate seamlessly with a persistent bi-temporal Second Brain combining:

Dense Vector Memory (FAISS IndexFlatIP) with Maximal Marginal Relevance (MMR) deduplication.
Neuro-Symbolic Knowledge Graph (NetworkX Personalized PageRank / PPR) for multi-hop entity association.
Playwright Set-of-Marks ([#som_id]) Browser Grounding and Voyager-style Dynamic Skill Synthesis.

🏗️ Architecture & Training Specifications

Property	Specification
Base Architecture	`Lfm3ForCausalLM` (Tri-Hybrid: Gated `shortconv` + Sliding-Window GQA + Full GQA)
Parameters	~1.7 Billion (`24` Layers, `2048` Hidden Dim, `7680` SwiGLU FFN Dim)
Attention Heads	`16` Query Heads / `4` Key-Value Heads (GQA) on Attention Layers
ShortConv Cache	Kernel Size `L_cache = 7`
Vocabulary Size	`125,050` (Native Byte-Level BPE via `PreTrainedTokenizerFast`)
Max Context Length	524,288 tokens (512K) via NTK-YaRN (`factor=2.0`, `mscale=1.14`)
Stage 1 Post-Training	Multi-Turn Supervised Fine-Tuning (SFT) on 4-Stage `<think>` + `<tool_call>` trajectories (`LoRA r=32, alpha=64, lr=1.5e-4`, final loss `0.089`)
Stage 2 Post-Training	Group Relative Policy Optimization (GRPO) with Dense AST, Signature-Binding & Context-Grounding Rewards (`num_generations=4, lr=5e-6`)

🔍 Example Model Output (Multi-Turn Agentic Trace)

Turn 1: Autonomous Planning & Tool Execution

<think>
[1. CONTEXT & 2ND BRAIN AUDIT]: <context> indicates the workspace is clean and report.txt is not yet written. <second_brain> lists the target URL https://example.com/.
[2. DAG DECOMPOSITION]:
  - Step 1: Call `browser_goto(url='https://example.com')` to extract the live Set-of-Marks DOM.
  - Step 2: Call `computer_write_file(filename='report.txt', content=dom_snap)` to persist the DOM.
  - Step 3: Call `computer_bash(command='head -n 8 report.txt')` to verify the file on disk.
[3. HALLUCINATION & CONSTRAINT CHECK]: All URLs and filenames are explicit and match tool parameter schemas.
[4. PRECISION EXECUTION]: Emit executable Python inside <tool_call>.
</think>
<tool_call>
dom_snap = browser_goto(url="https://example.com")
write_res = computer_write_file(filename="report.txt", content=dom_snap)
verify_res = computer_bash(command="head -n 8 report.txt")
print(write_res)
print(verify_res)
</tool_call>

Turn 2: Grounded Synthesis After `<tool_response>`

<think>
[1. CONTEXT & 2ND BRAIN AUDIT]: <tool_response> confirms report.txt (1068 bytes) was written and verified with EXIT 0.
[2. DAG DECOMPOSITION]: All 3 DAG nodes succeeded; no further tool calls required.
[3. HALLUCINATION & CONSTRAINT CHECK]: Cite exact byte count (1068 bytes), page title (Example Domain), and Set-of-Marks [#1].
[4. PRECISION EXECUTION]: Output final verified Markdown summary.
</think>
### Execution Verified
1. **Browser Navigation:** Loaded `https://example.com/` (`Example Domain`).
2. **Second Brain Upgrade:** Saved interactive Set-of-Marks `[#1]` (`<a> "Learn more"`).
3. **File Write:** Persisted `report.txt` — `1068 bytes`.
4. **Disk Verification:** Confirmed `report.txt` exists (`EXIT 0`).

📦 Available GGUF Quantizations

All GGUF files are hosted in the companion repository: mohommed/LFM3-1.7B-Frontier-SmartAgent-GGUF.

💡 Quantization Recommendation: Because LFM3-1.7B is a compact 1.7B Tri-Hybrid model utilizing stateful gated short-convolution (shortconv) layers, Q8_0 (1.84 GiB) or Q6_K (1.42 GiB) is strongly recommended to retain 99.8% of full-precision coding, reasoning, and tool-calling accuracy.

Filename	Quantization	Size	Best Use Case
`lfm3-1.7b-frontier-f16.gguf`	`F16`	~3.45 GiB	Uncompressed 16-bit reference weights
`lfm3-1.7b-frontier-q8_0.gguf`	`Q8_0`	~1.84 GiB	⭐ Recommended for SOTA Agentic & Coding Quality
`lfm3-1.7b-frontier-q6_k.gguf`	`Q6_K`	~1.42 GiB	Near-lossless quality with low memory footprint
`lfm3-1.7b-frontier-q5_k_m.gguf`	`Q5_K_M`	~1.22 GiB	Balanced quality and inference speed
`lfm3-1.7b-frontier-q4_k_m.gguf`	`Q4_K_M`	~1.02 GiB	Fast CPU / laptop deployment
`lfm3-1.7b-frontier-q3_k_m.gguf`	`Q3_K_M`	~0.82 GiB	Ultra-compact mobile & embedded devices

🚀 Quickstart Guide

1. Python (`transformers`)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mohommed/LFM3-1.7B-Frontier-SmartAgent"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    torch_dtype=torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16,
    device_map="auto",
).eval()

system_prompt = """You are LFM3-1.7B-Frontier, an elite autonomous AI agent equipped with a 512K context window and a Real-Time Second Brain Memory system.

### MANDATORY 4-STAGE THINKING PROTOCOL
Inside `<think>...</think>`, structure your reasoning using:
[1. CONTEXT & 2ND BRAIN AUDIT]
[2. DAG DECOMPOSITION]
[3. HALLUCINATION & CONSTRAINT CHECK]
[4. PRECISION EXECUTION]"""

messages = [
    {"role": "system", "content": system_prompt},
    {
        "role": "user",
        "content": (
            "<context>Workspace active.</context>\n"
            "<second_brain>No cached memories.</second_brain>\n"
            "Goal: Write a thread-safe LRU cache in Python with O(1) get and put operations."
        ),
    },
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.15,
        top_p=0.90,
        repetition_penalty=1.08,
        do_sample=True,
        pad_token_id=tokenizer.eos_token_id,
    )

reply = "<think>\n" + tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=False).split("<|im_end|>")[0].strip()
print(reply)

2. Ollama (GGUF)

# Run the recommended 8-bit quantization directly from Hugging Face:
ollama run hf.co/mohommed/LFM3-1.7B-Frontier-SmartAgent-GGUF:Q8_0

# Or run the 4-bit quantization:
ollama run hf.co/mohommed/LFM3-1.7B-Frontier-SmartAgent-GGUF:Q4_K_M

3. `llama.cpp` CLI

./llama-cli \
  -hf mohommed/LFM3-1.7B-Frontier-SmartAgent-GGUF:Q8_0 \
  -c 32768 \
  --temp 0.15 \
  --repeat-penalty 1.08 \
  -cnv

🛡️ Best Practices & Recommended Sampling Parameters

Temperature: 0.10 – 0.20 (Low temperature keeps AST code generation and tool parameter binding deterministic).
Top-P: 0.90 – 0.92
Repetition Penalty: 1.08
Context Packing: While the architecture supports up to 512K tokens, for single-GPU consumer hardware (8 GB–16 GB VRAM), pairing the model with FAISS + PageRank MMR retrieval (injecting the top 8K–32K highest-signal tokens per turn) maximizes prefill speed and attention sharpness.

📜 License & Citation

This model is released under the Apache-2.0 License, inheriting from LiquidAI/LFM3-1.7B.

@misc{lfm3_frontier_smartagent_2026,
  title        = {LFM3-1.7B-Frontier-SmartAgent: 512K-Context Hybrid Reasoning and Second-Brain Autonomous Agent},
  author       = {mohommed},
  year         = {2026},
  publisher    = {Hugging Face},
  howpublished = {\url{https://huggingface.co/mohommed/LFM3-1.7B-Frontier-SmartAgent}}
}

Downloads last month: 546

Safetensors

Model size

2B params

Tensor type

F16

Model tree for mohommed/LFM3-1.7B-Frontier-SmartAgent

Base model

LiquidAI/LFM3-1.7B-Base

Finetuned

LiquidAI/LFM3-1.7B

Quantized

(58)

this model

Quantizations

3 models

🚀 LFM3-1.7B-Frontier-SmartAgent (512K Context • 4-Stage Reasoning • Second Brain Agent)

✨ Key Architectural Highlights

1. 🔭 512K (524,288 Token) NTK-Aware YaRN Context Scaling

2. 🧭 Gram-Schmidt Damped SVD Orthogonalization (Layers 9–19)

3. 🧠 Mandatory 4-Stage Frontier <think> Protocol

4. 🕸️ HippoRAG-2 Associative "Second Brain" & Multi-Hop Deep Research Ready

🏗️ Architecture & Training Specifications

🔍 Example Model Output (Multi-Turn Agentic Trace)

Turn 1: Autonomous Planning & Tool Execution

Turn 2: Grounded Synthesis After <tool_response>

📦 Available GGUF Quantizations

🚀 Quickstart Guide

1. Python (transformers)

2. Ollama (GGUF)

3. llama.cpp CLI

🛡️ Best Practices & Recommended Sampling Parameters

📜 License & Citation

Model tree for mohommed/LFM3-1.7B-Frontier-SmartAgent

3. 🧠 Mandatory 4-Stage Frontier `<think>` Protocol

Turn 2: Grounded Synthesis After `<tool_response>`

1. Python (`transformers`)

3. `llama.cpp` CLI