LFM3-1.7B

LFM3-1.7B is a text model for local agents and specialized applications, based on our new tri-hybrid architecture.

  • Agentic training: post-trained for agentic harnesses such as Hermes Agent, Pi, and OpenClaw, with a 256K-token context window.
  • Designed for the edge: at 4-bit precision, it takes about 1 GB of memory, so it fits on any phone or laptop.
  • Made to be specialized: adapt the model to your domains, formats, and tools via quick single-GPU fine-tuning.

Find more information about the LFM3 family in our release blog post.

Model details


The LFM3 family includes base, text, vision, audio, omni, and decision models.

Property Specification
Checkpoint Post-trained, text-only language model
Parameters 1.73B
Architecture 24 layers: 13 gated short convolutions, 5 sliding-window attention, 6 global attention
Context length 256K tokens (input + output)
Vocabulary 128,000 tokens
Languages English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, Polish
License LFM Open License v1.0

LFM3-1.7B is designed for local agents, tool calling, structured outputs, and domain-specific fine-tuning. Use retrieval or search for knowledge-heavy tasks. It is not recommended for agentic coding or complex multi-step reasoning due to its small size.

Inference


Use these ONNX weights with Transformers.js v4.3.2 or later. The example below uses the text generation pipeline with WebGPU.

npm install @huggingface/transformers@^4.3.2
import { pipeline, TextStreamer } from "@huggingface/transformers";

// Create a text generation pipeline.
const generator = await pipeline(
  "text-generation",
  "onnx-community/LFM3-1.7B-ONNX",
  { dtype: "q4f16", device: "webgpu" },
);

const messages = [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "What is the capital of France?" },
];

// Generate and stream a response.
const output = await generator(messages, {
  max_new_tokens: 512,
  do_sample: true,
  temperature: 0.1,
  top_k: 50,
  repetition_penalty: 1.1,
  tokenizer_encode_kwargs: { enable_thinking: false },
  streamer: new TextStreamer(generator.tokenizer, {
    skip_prompt: true,
    skip_special_tokens: true,
  }),
});
console.log(output[0].generated_text.at(-1).content);

// Release the model when you are finished using it.
await generator.dispose();

The pipeline applies the chat template automatically. This example disables thinking with tokenizer_encode_kwargs: { enable_thinking: false }. Set enable_thinking: true and increase max_new_tokens when you want to allow a longer reasoning trace.

Fine-tuning


LFM3-1.7B is designed for easy customization for a given domain, task, or application via TRL.

Training Use case Notebook
SFT Extract structured JSON from messy documents Open in Colab
DPO Answer from retrieved documents, or decline Open in Colab
GRPO Call the right tools in a 108-tool phone app Open in Colab
CPT Learn a new language (Turkish) from raw text Open in Colab

Performance


Benchmarks

LFM3-1.7B can power agentic applications that used to need 9B parameters.

Benchmark LFM3
1.7B
LFM2.5
2.6B
MiniCPM5
2B
Gemma 4
E4B
Qwen3.5
4B
Qwen3.5
9B
Agents
LiveClaw 45.60 14.70 30.37 20.36 19.94 35.77
Claw-Eval General (EN), average 68.64 62.63 60.74 56.14 61.96 66.53
Claw-Eval General (EN), pass^3 51.40 37.52 34.58 22.43 42.99 51.87
BrowseComp-Plus (OpenClaw subset) 37.00 26.33 16.83 21.00 24.67 38.00
WebArena-Verified 38.42 3.02 9.11 17.06 21.92 28.94
EnterpriseOps-Gym 28.20 7.94 13.41 9.86 25.96 28.97
AutomationBench (public) 41.29 0.94 4.71 1.92 8.67 15.10
Tool use
BFCL V4 71.39 55.89 62.65 48.25 55.12 62.83
ToolSandbox 80.36 78.04 68.16 69.27 75.40 76.41
MCP-Atlas 32.57 16.45 26.38 6.19 41.37 42.67
ฯ„ยณ-bench (4 domains), average 68.01 56.77 69.44 33.53 65.98 67.11
Agentic coding
SWE-bench Verified (OpenCode) 43.40 18.00 34.80 0.50 41.20 51.20
SWE-bench Multilingual (OpenCode) 23.00 8.00 15.67 0.67 23.33 35.00
Terminal-Bench 2.1 (OpenCode) 12.92 0.00 5.62 0.00 13.48 17.98
Coding
LiveCodeBench v6 73.46 60.57 70.52 71.00 61.99 69.86
LiveCodeBench Pro 25Q231.7419.1629.3429.9424.2534.43
SciCode 28.47 16.32 27.78 25.00 23.02 31.60
Instruction following
IFEval96.6695.3987.8390.0292.5292.08
IFBench73.0360.4862.0844.5638.1648.84
IFStruct93.7282.1872.6578.4587.0589.20
Multi-IF 89.10 84.80 73.19 81.03 80.32 84.44
Knowledge
GPQA Diamond63.3757.7865.1557.8875.7680.40
Humanity's Last Exam (no tools)7.175.888.204.7712.8416.41
Humanity's Last Exam (with tools)13.909.6011.506.0011.6017.50
AA-Omniscience (public)0.50-33.17-5.00-15.33-57.17-28.00
AA-Omniscience accuracy (public)7.078.759.139.8315.6713.17
AA-Omniscience non-hallucination (public)92.9353.6984.4472.0913.6452.59
Long context
AA-LCR 52.83 6.00 49.34 39.33 52.67 62.00
RULER 128K 65.56 1.15 37.96 18.82 84.63 87.11
Average49.3731.5539.1931.7439.2747.24
Evaluation details

All models were served with vLLM in BF16 at their full context length: 262,144 tokens for LFM3-1.7B, Qwen3.5-4B, and Qwen3.5-9B, and 131,072 tokens for LFM2.5-2.6B, MiniCPM5-2B, and Gemma 4 E4B. Unless listed below, every eval uses temperature 0.6 and top_p 0.95, with no output limit other than the context length. The Average row is the unweighted mean of every score in the table.

BFCL V4: greedy decoding, up to 32,768 output tokens.
ToolSandbox: greedy decoding, up to 1,024 tokens per turn.
LiveClaw: OpenClaw agent, up to 8,192 tokens per turn.
Claw-Eval: greedy decoding, 3 trials per task.
BrowseComp-Plus: OpenClaw agent, greedy decoding, up to 8,192 tokens per turn.
WebArena-Verified: up to 40 steps.
MCP-Atlas: up to 256 turns.
EnterpriseOps-Gym and AutomationBench: up to 50 turns.
SWE-bench: OpenCode agent, up to 250 turns.
Terminal-Bench 2.1: OpenCode agent, up to 100 turns.

Edge inference

At 32K context, LFM3-1.7B prefills at least 2.5x faster and decodes at least 1.8x faster than every compared model on all three devices, while using the least memory.

LFM3-1.7B edge inference at 32K context: prefill throughput, decode throughput, and host plus GPU memory on AMD Ryzen AI Max+ 395, Apple M5 Max, and iPhone 17 Pro, compared with MiniCPM5-2B, Qwen3.5-4B, Qwen3.5-9B, and Gemma 4 E4B.
Evaluation details

All models run as Q4_0 GGUF files in llama.cpp with 32,768 tokens of context, batch size 1, 100 output tokens, and GPU offload. Prefill is the prompt processing speed and decode is the generation speed, both in tokens per second. LFM3-1.7B uses a llama.cpp build with LFM3 support, and the other models use llama.cpp release b11744.

AMD Ryzen AI Max+ 395: Radeon 8060S integrated GPU, Windows, Vulkan backend.
Apple M5 Max: macOS, Metal backend.
iPhone 17 Pro: Apple A19 Pro, iOS app built on llama.cpp.
Memory: peak usage in GB (109 bytes). On AMD, it adds the host and GPU peaks from the same run, which can slightly overstate usage if the two peaks do not coincide. On Apple devices, the process footprint already includes Metal allocations.

GPU inference

At 1,024 concurrent requests, LFM3-1.7B can produce 3.6 billion tokens/day on one NVIDIA B300.

LFM3-1.7B GPU inference: output throughput versus concurrent requests on one NVIDIA B300, compared with MiniCPM5-2B, Gemma 4 E4B, Qwen3.5-4B, and Qwen3.5-9B.

Training


LFM3-1.7B pre-training: web and synthetic data (about 15T tokens), then code, math, and science (3T tokens at 4K context), followed by mid-training on curated agentic data (3T tokens at 32K context), a 128K extension (500B tokens), and a 256K extension (50B tokens), for 22T tokens in total.

Pre-training: two stages build LFM3-1.7B-Base on 22T tokens in total.

  • Main pre-training: compared with LFM2, the mix adds more scientific papers, repository-level code, math, and a wider range of knowledge sources.
  • Mid-training: the last 3.5T tokens use curated, higher-quality data with a larger share of agentic traces and tool calls. This stage also extends the context window to 256K tokens.
LFM3-1.7B post-training recipe: the student goes through SFT and mixed RL, specialist RL teachers such as math, code, and tool RL start from the mixed RL checkpoint, MOPD distills them back into the student, and agentic RL comes last.

Post-training: four stages develop conversation, reasoning, and tool-use capabilities.

  • Supervised fine-tuning (SFT): 1.75T tokens across various tasks, including chat, reasoning, tool calling, and agentic traces.
  • Mixed reinforcement learning: many domains trained at once, from math and code to SQL and structured outputs. A length penalty in the reward keeps answers concise.
  • Multi-domain on-policy distillation (MOPD): six specialist RL teachers (code, math, tool use, long context, agentic work, and enterprise workflows) are distilled back into a single model.
  • Agentic RL: tasks from web browsing to office work are run inside real agent harnesses, preparing the model for deployment.

Citation


@article{liquidAI2026LFM3,
  author  = {Liquid AI},
  title   = {Introducing LFM3: Every Modality for Specialized Intelligence},
  journal = {Liquid AI Blog},
  year    = {2026},
  note    = {www.liquid.ai/blog/lfm3},
}

For questions and feedback, join Discord. For custom deployment and fine-tuning support, contact Liquid AI.

Downloads last month
1,964
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for onnx-community/LFM3-1.7B-ONNX

Quantized
(158)
this model

Space using onnx-community/LFM3-1.7B-ONNX 1