whatmodel.sh / LFM2 700M

LFM2 700M

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

LFM2 700M is an open-weights language model from Liquid AI, released July 2025. Its published size is 0.742B parameters and a 33k-token context window. Licence: lfm1.0.

Catalogue identity notes

LiquidAI/LFM2-700M @86f49fc (created 2025-07-10, licence lfm1.0). Liquid AI LFM2 hybrid (conv + attention) instruct model, July-Sept 2025; earlier generation than the catalogued LFM2.5 models. Lab rows from the LFM2-1.2B card's own LFM2 columns (3-model runs) plus independent EuroEval rows.

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 742,489,344 parameters (LiquidAI/LFM2-700M @86f49fc).

36.1±1.5#590 of 719 LLMsfrom 10 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of LFM2 700M, out of 828 with a score, then more from Liquid AI.

#modelscorewhereRAMreleased
682LLaMA 33B Meta36±1comparison only2023-02
683Code Llama 7B Instruct Meta36±1local~5.5GB2023-08
684LFM2 700M Liquid AI36±2local~1.9GB2025-07
685Granite 3.2 2B Instruct IBM36±1local~3GB2025-02
686Mistral 7B Instruct v0.2 Mistral36±1local~6GB2023-12
more from Liquid AI
370LFM2.5 2.6B Liquid AI53±1local~3.2GB2026-07
375LFM2.5 8B-A1B Liquid AI52±1local~6.5GB2026-05
398LFM2 24B-A2B Liquid AI51±1local~16GB2026-02

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #277 of 393 * · 7.8% of its score · 1 test

Beats Ministral 3 14B Reasoning 2512, Gemma 4 E4B, Ministral 3 8B here, though they rank higher overall. Trails Flan-T5 XXL here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
IFEval (aggregation unspecified) lab72.2% ✎▄····█▄···▄█ beats 4/6easy · avg 82%▇▇▇ 7.8%at its level
math▁▂▃▅▆▅▄█▄▁▁▁ #333 of 398 * · 33% of its score · 2 tests

Beats GPT-3.5 Turbo (0125), Qwen2-VL 7B Instruct, DBRX Instruct here, though they rank higher overall. Trails Qwen3 0.6B, Gemma 7B (base) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
MGSM lab45.4% ✎█···█▄··▄··▄ beats 4/6easy · avg 77%▇▇▇▇▇▇▇▇▇ 23%at its level
GSM8K lab46.4% ✎▄·█···▄·▄··█ beats 3/6easy · avg 83%▇▇▇▇ 11%sharp · at its level
other tests7 not in a task · 58% of its score
testresultvs the others in its rundifficultycountswhy
MMLU lab49.9% ✎█·███·█··█·█ beats 4/6easy · avg 75%▇▇▇▇▇▇▇▇▇ 21%at its level
MMMLU lab43.3% ✎▄···▄·▄▄··▄█ beats 4/6medium · avg 59%▇▇▇▇ 10%typical
IFBench (aggregation unspecified) lab20.6% ✎▄▄·▄····▄·█▄ beats 4/6medium · avg 40%▇▇▇▇ 9.3%typical
GPQA (subset unspecified) lab28.5% ✎█······▄▄█·▄ beats 4/6hard · avg 39%▇▇▇ 6.3%sharp · too hard for it · noisy
Open PT-LLM Leaderboard average (9 Portuguese tasks)55.0% ✎▃▁▁▁▁▁▁▁▃█▅▁ beats 76/276medium · avg 73%▇▇ 4.2%at its level · noisy
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy42.1% ✎▁▁▁▁▁▃▁▂▄█▄▃ beats 14/146easy · avg 83%▇ 3.4%at its level · noisy
EuroEval HellaSwag (English), test split, 5-shot generative MC, accuracy25.1% ✎▃·▁▁▂▁▂▅█▇▄▁ beats 5/100medium · avg 68%▇ 2.8%noisy

$ where to run it

llama.cpp · recommended

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run LFM2 700M · needs ~0.47 GB · from huggingface.co/LiquidAI (official)
    chat in the terminal
    llama cli -hf LiquidAI/LFM2-700M-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf LiquidAI/LFM2-700M-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run LFM2 700M · needs ~0.47 GB · from huggingface.co/LiquidAI (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/LiquidAI/LFM2-700M-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run LFM2 700M · needs ~0.47 GB · from huggingface.co/LiquidAI (official)
    chat in the terminal
    ollama run hf.co/LiquidAI/LFM2-700M-GGUF:Q4_K_M

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run LFM2 700M · needs ~0.4 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/LFM2-700M-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/LFM2-700M-4bit

Official weights and documentation: huggingface.co/LiquidAI ↗

$ how the score was worked out · LiquidAI/LFM2-1.2B model card 88%, EuroEval leaderboards (result… 6%, Open Portuguese LLM Leaderboa… 4%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
LiquidAI/LFM2-1.2B model card · lab-reported7▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 88%LFM Open License v1.0
EuroEval leaderboards (results collection), English generative leaderboard2▇▇ 6%MIT
Open Portuguese LLM Leaderboard (archived)1▇ 4%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 36.1

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json