Marketplace · Text & chat

lfm3:latest

Call lfm3:latest through one OpenAI-compatible API. It's served by 3 hosts on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.

From
£0.043
per 1M output tokens
£1 buys about 23 million tokens (≈ 17 million words)
Hosts
3
Loaded now
0

At a glance.

tools reasoning

  • Type: Text & chat
  • Hosts serving it now: 3 (0 with it loaded in memory)
  • Engines: ollama
  • Context window: up to 262,144 tokens
  • Rentable: a whole host from £0.04 an hour (rentals)
python · openai sdk
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
                api_key=INPHERIO_API_KEY)
reply = client.chat.completions.create(
    model="lfm3:latest",
    messages=[{"role": "user", "content": "Hello"}],
)

lfm3:latest in detail.

LFM3-1.7B is a tri-hybrid model for local agents and specialized applications.

Published by
LiquidAI
Parameters
1.7B
Download size
1.1 GB (as packaged for Ollama)
Quantisation
Q4_K_M
Format
gguf
Architecture
lfm3
Licence
lfm1.0
Based on
LiquidAI/LFM3-1.7B-Base
Task
text generation
Library
transformers
Languages
en, ar, zh, fr, de, it, ja, ko, pt, es, vi, th
First published
23 Oct 2026
Last updated
3 Nov 2026
Downloads (30 days)
70,034 on Hugging Face
Likes
1,550

lfm3 text-generation liquid edge en ar zh fr de it ja ko pt es vi th

The model card

Published by the model's authors on Hugging Face — shown as they wrote it, unedited by Inpherio.

<img src="data:image/svg+xml,%3Csvg xmlns=%22http://www.w3.org/2000/svg%22 width=%2216%22 height=%2216%22 viewBox=%220 0 24 24%22 fill=%22none%22 stroke-width=%222.2%22 stroke-linecap=%22round%22 stroke-linejoin=%22round%22%3E%3Cstyle%3Epath%7Bstroke:%23000%7D%40media (prefers-color-scheme:dark)%7Bpath%7Bstroke:%23d1d5dc%7D%7D%3C/style%3E%3Cpath d=%22m8 6-6 6 6 6m8-12 6 6-6 6m-2-14-4 16%22/%3E%3C/svg%3E" width="16" height="16" alt="" aria-hidden="true" style="display: block; flex: 0 0 16px; width: 16px; height: 16px; margin: 0;" />API <img src="data:image/svg+xml,%3Csvg xmlns=%22http://www.w3.org/2000/svg%22 width=%2216%22 height=%2216%22 viewBox=%220 0 24 24%22 fill=%22none%22 stroke-width=%222.2%22 stroke-linecap=%22round%22 stroke-linejoin=%22round%22%3E%3Cstyle%3Epath%7Bstroke:%23000%7D%40media (prefers-color-scheme:dark)%7Bpath%7Bstroke:%23d1d5dc%7D%7D%3C/style%3E%3Cpath transform=%22translate(3 0)%22 d=%22M8 5.5v13L19 12 8 5.5Z%22/%3E%3C/svg%3E" width="16" height="16" alt="" aria-hidden="true" style="display: block; flex: 0 0 16px; width: 16px; height: 16px; margin: 0;" />Try <img src="data:image/svg+xml,%3Csvg xmlns=%22http://www.w3.org/2000/svg%22 width=%2216%22 height=%2216%22 viewBox=%220 0 24 24%22 fill=%22none%22 stroke-width=%222.2%22 stroke-linecap=%22round%22 stroke-linejoin=%22round%22%3E%3Cstyle%3Epath%7Bstroke:%23000%7D%40media (prefers-color-scheme:dark)%7Bpath%7Bstroke:%23d1d5dc%7D%7D%3C/style%3E%3Cpath d=%22M12 6c-3-2-6-2.5-10-2v15c4-.5 7 0 10 2m0-15c3-2 6-2.5 10-2v15c-4-.5-7 0-10 2V6Z%22/%3E%3C/svg%3E" width="16" height="16" alt="" aria-hidden="true" style="display: block; flex: 0 0 16px; width: 16px; height: 16px; margin: 0;" />Docs <img src="data:image/svg+xml,%3Csvg xmlns=%22http://www.w3.org/2000/svg%22 width=%2216%22 height=%2216%22 viewBox=%220 0 24 24%22 fill=%22none%22 stroke-width=%222.2%22 stroke-linecap=%22round%22 stroke-linejoin=%22round%22%3E%3Cstyle%3Epath%7Bstroke:%23000%7D%40media (prefers-color-scheme:dark)%7Bpath%7Bstroke:%23d1d5dc%7D%7D%3C/style%3E%3Cpath transform=%22translate(1 0)%22 d=%22m16 3 5 5L8 21H3v-5L16 3Zm-3 3 5 5%22/%3E%3C/svg%3E" width="16" height="16" alt="" aria-hidden="true" style="display: block; flex: 0 0 16px; width: 16px; height: 16px; margin: 0;" />Blog

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.

Read the rest of the model card

Inference

Choose a checkpoint variant for your inference framework and hardware.

Checkpoint Framework Description

BF16 vLLM, SGLang, Transformers BF16 weights for GPU inference.

FP8 SGLang FP8 quantization for GPU inference.

NVFP4 SGLang 4-bit floating-point quantization for GPU inference.

GGUF llama.cpp, Ollama, LM Studio Local inference on CPUs and GPUs.

MLX MLX 4-bit quantization for Apple Silicon.

ONNX ONNX Runtime Cross-platform inference with ONNX Runtime.

Sampling parameters:

  • General (chat, tool use, agents, coding): temperature=0.1,top_k=50, repetition_penalty=1.1
  • Math & STEM (math, science): temperature=1.0, top_p=0.95, top_k=20

Transformers quick start:

from transformers import pipeline

generator = pipeline(
    "text-generation",
    model="LiquidAI/LFM3-1.7B",
    trust_remote_code=True,
)

messages = [{"role": "user", "content": "What is C. elegans?"}]
output = generator(
    messages,
    do_sample=True,
    temperature=0.1,
    top_k=50,
    repetition_penalty=1.1,
    max_new_tokens=2048,
)
print(output[0]["generated_text"][-1]["content"])

For local agent setup, see the Agent Harnesses guide.

Chat template

LFM3 uses this ChatML format, generated from the checkpoint's chat template:

<|startoftext|><|im_start|>system
You are a helpful assistant trained by Liquid AI.<|im_end|>
<|im_start|>user
Explain how a heat pump works.<|im_end|>
<|im_start|>assistant

Use tokenizer.apply_chat_template() with add_generation_prompt=True to format messages automatically.

Reasoning is enabled by default. You can set enable_thinking=False to disable thinking traces, but this behavior can be inconsistent, especially for reasoning-heavy tasks.

Reasoning from turns before the latest user message is removed unless preserve_thinking=True.

Tool calling

Pass function schemas through tools=... to apply_chat_template(). The template formats tool definitions and results automatically. Generated calls use XML:


Paris

Execute the call in your application. Add the parsed assistant call to history as a tool_calls entry, then append the result as a tool message. Keep passing the tool schemas on subsequent requests and preserve the assistant's content and reasoning from the current tool-use turn.

function.arguments must be a Python mapping. Decode JSON strings with json.loads() before applying the template.

Tool search

LFM3 supports deferred tools. Set defer_loading=True to keep tool definitions out of the prompt until your harness's search tool returns their names as tool_reference parts. The chat template then inserts their definitions into ``.

tools = [
    search_tool,
    {"type": "function", "defer_loading": True, "function": get_weather_schema},
]
messages.append({
    "role": "tool",
    "tool_call_id": call_id,
    "content": [
        {"type": "text", "text": "Found 1 tool."},
        {"type": "tool_reference", "name": "get_weather"},
    ],
})

Your harness implements and runs the search. Keep the full tools list, including deferred tools, on every request. In the system prompt, tell the model when to search:

You only have one tool right now: search_tools, which searches a catalog of many more tools. If none of your current tools can handle a request, call search_tools to find one, then call the tool it returns.

Works with vLLM, SGLang, and LFM3-compatible llama.cpp builds. For llama.cpp, use a GGUF with the current chat template or load it with --chat-template-file.

See Deferred tools and tool search for the full guide.

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

DPO Answer from retrieved documents, or decline

GRPO Call the right tools in a 108-tool phone app

CPT Learn a new language (Turkish) from raw text

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

τ³-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.

<img src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/lfm3-edge-inference.webp" alt="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." width="4200" height="4223" style="width: 100%; max-width: 4200px; height: auto;" />

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.

Training

<img src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/lfm3-pre-training-recipe.webp" alt="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." width="2000" height="754" style="width: 100%; max-width: 2000px; height: auto;" />

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.

<img src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/lfm3-post-training-recipe.webp" alt="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." width="2000" height="924" style="width: 100%; max-width: 2000px; height: auto;" />

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.

Sources: LiquidAI/LFM3-1.7B on Hugging Face · lfm3:latest on Ollama. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.

Who's serving it.

Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.

Hosts serving lfm3:latest right now
HostTierPriceMeasured speedHealthStateRent
GTX 1080 Ti (11G)L1£0.022 in · £0.043 out77 tok/s · 59 ms first token78loads on request£0.60/h
W11BOXL1£0.03 in · £0.06 out19 tok/s · 343 ms first token77loads on request—
7B-A1B (5G)L1£0.062 in · £0.25 out18 tok/s · 482 ms first token82loads on request£0.04/h

Live data, refreshed on every visit. How billing works.

Room on the grid for your machine.

3 machines serve lfm3:latest today. Every extra host is somewhere a request can fail over to when one drops, and spare capacity when demand spikes. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.

Hosts now
3
0 loaded in memory
Price to beat
£0.043
per 1M output tokens
Fastest measured
77 tok/s

Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load lfm3:latest, and the platform benchmarks it on your hardware before your first request.