whatmodel.sh / LFM2.5 1.2B Thinking

LFM2.5 1.2B Thinking

+ contribute

LFM2.5 1.2B Thinking is an open-weights language model from Liquid AI, released January 2026. Its published size is 1.17B parameters and a 33k-token context window. Licence: lfm1.0.

48.9±1.8#362 of 719 LLMsfrom 10 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of LFM2.5 1.2B Thinking, out of 828 with a score, then more from Liquid AI.

#	model	score	where	RAM	released
431	OpenCodeInterpreter-DS-6.7B M-A-P	49±1	local	~5.8GB	2024-02
432	Artigenz-Coder-DS-6.7B Artigenz	49±1	local	~5.8GB	2024-04
433	LFM2.5 1.2B Thinking Liquid AI	49±2	local	~2.2GB	2026-01
434	Qwen3-VL 2B Thinking Alibaba	49±1	local	~2.7GB	2025-10
435	speechless-codellama-34b-v2.0 uukuguy	49±1	local	~23GB	2023-10
	more from Liquid AI
370	LFM2.5 2.6B Liquid AI	53±1	local	~3.2GB	2026-07
375	LFM2.5 8B-A1B Liquid AI	52±1	local	~6.5GB	2026-05
398	LFM2 24B-A2B Liquid AI	51±1	local	~16GB	2026-02

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #216 of 300 * · 3.1% of its score · 1 test

Beats o1 (2024-12-17), o3-mini, DeepSeek R1 (Jan '25) here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
BFCL v3 lab	57.0% ✎	▄▄·······▄██ beats 6/6	medium · avg 56%	▇ 3.1%	blunt · at its level

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #140 of 393 * · 8.0% of its score · 1 test

Beats INTELLECT-3, Nemotron 3 Super 120B-A12B, MiniMax-M2 here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
IFEval mean of four measures lab	88.4% ✎	█·█··█·██·██ beats 6/6	very easy · avg 87%	▇▇▇ 8.0%	typical

math▁▂▃▅▆▅▄█▄▁▁▁ #210 of 398 · 38% of its score · 3 tests

Beats DeepSeek V3 (Dec '24), GPT-4o (2024-08-06), Command A (03-2025) here, though they rank higher overall. Trails Olmo 3 7B Instruct, DeepSeek R1 Distill Llama 8B, Phi-4-mini-reasoning 3.8B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
GSM8K lab	85.6% ✎	█····▄▄▄···█ beats 6/6	very easy · avg 87%	▇▇▇▇▇▇▇ 17%	sharp
AIME 2025 lab	31.7% ✎	▄█··▄···▄··█ beats 5/6	hard · avg 33%	▇▇▇▇▇▇ 14%	sharp · at its level · noisy
MATH-500 lab	88.0% ✎	▄··█▄·▄···▄▄ beats 6/6	easy · avg 80%	▇▇▇ 7.0%	typical

other tests5 not in a task · 49% of its score

test	result	vs the others in its run	difficulty	counts	why
GPQA Diamond lab	37.9% ✎	█··········█ beats 4/5	hard · avg 41%	▇▇▇▇▇▇▇ 18%	sharp · noisy
MMLU-Pro lab	49.6% ✎	█···█·██·███ beats 5/6	medium · avg 54%	▇▇▇▇▇ 13%	at its level
IFBench (aggregation unspecified) lab	44.9% ✎	▄·█·█······█ beats 5/6	medium · avg 43%	▇▇▇▇ 11%	at its level
EuroEval HellaSwag (English), test split, 5-shot generative MC, accuracy	38.9% ✎	▃·▁▁▂▃▂▅█▇▄▁ beats 20/100	medium · avg 68%	▇▇ 4.9%	at its level · noisy
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy	75.2% ✎	▁▁▁▁▁▁▁▂▄█▄▃ beats 50/146	easy · avg 83%	▇ 3.3%	noisy

$ where to run it

llama.cpp · recommended

version

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 ↗
Run LFM2.5 1.2B Thinking · needs ~0.7 GB · from huggingface.co/LiquidAI (official)
chat in the terminal
llama cli -hf LiquidAI/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf LiquidAI/LFM2.5-1.2B-Thinking-GGUF:Q4_K_M

LM Studio

version

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run LFM2.5 1.2B Thinking · needs ~0.7 GB · from huggingface.co/LiquidAI (official)
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking-GGUF@Q4_K_M -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run LFM2.5 1.2B Thinking · needs ~1.2 GB · from ollama.com
chat in the terminal
ollama run lfm2.5-thinking:1.2b

MLX (Mac)

version

Install MLX (Mac) · Apple silicon Macs only, text only.
with uv
uv tool install mlx-lm
or
pip install mlx-lm
Run LFM2.5 1.2B Thinking · needs ~0.7 GB, Mac only · from huggingface.co/LiquidAI (official)
chat in the terminal
mlx_lm.chat --model LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit
Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit

Official weights and documentation: huggingface.co/LiquidAI ↗

$ how the score was worked out · LiquidAI/LFM2.5-1.2B-Thinking… 90%, EuroEval leaderboards (result… 8%

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

source	results	share of the score	licence
LiquidAI/LFM2.5-1.2B-Thinking model card · lab-reported	8	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 90%	LFM Open License v1.0
EuroEval leaderboards (results collection), English generative leaderboard	2	▇▇ 8%	MIT
prior · pull toward the middle		▇ 1%
weighted average		= 48.9

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit 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 2026-10-11 02:20 UTC · sources and licences · json