Compare / LFM2.5 1.2B Thinking vs Gemma 3 1B

LFM2.5 1.2B Thinking vs Gemma 3 1B

Updated November 2026

Verdict

LFM2.5 1.2B Thinking scores higher on the Small LM Index: 30.1 vs 6.1. On the 2 benchmarks both labs report, LFM2.5 1.2B Thinking wins 2 and Gemma 3 1B wins 0. Both need about 1.3 GB of memory at 4-bit quantization. Neither model has a hosted API on OpenRouter, so you would run both yourself.

Pick LFM2.5 1.2B Thinking if…

you want the strongest model overall

Pick Gemma 3 1B if…

you want the more widely used model (more quantized builds and community support)

Specifications

	LFM2.5 1.2B Thinking	Gemma 3 1B
Small LM Index	30.1 (likely 27–34)	6.1 (likely 5–8)
Lab	Liquid AI · United States	Google · United States
Released	2026-01-20	2025-03-12
Parameters	1.2B (dense)	1B (dense)
Memory at 4-bit	~1.3 GB	~1.2 GB
Context window	32K tokens	32K tokens
Input	text	text
Reasoning	Always thinks	No thinking
License	LFM Open License	Gemma
API price / 1M tokens	Self-host only	Self-host only
Hugging Face downloads (30 days)	8.1K	212.6K

Benchmarks

Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.

Benchmark	LFM2.5 1.2B Thinking	Gemma 3 1B
MMLU-Pro Knowledge	49.7	14.7
GPQA Diamond Knowledge	37.9	19.2
AIME Math	31.7	≈ 1
LiveCodeBench Coding	≈ 32	1.9
IFBench Instruction following	44.9	—
IFEval Instruction following	88.4	—
BFCL Agentic	57.0	—
MATH-500 Math	88.0	—

Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.

Questions

Which is better, LFM2.5 1.2B Thinking or Gemma 3 1B?

LFM2.5 1.2B Thinking scores higher on the Small LM Index: 30.1 vs 6.1. On the 2 benchmarks both labs report, LFM2.5 1.2B Thinking wins 2 and Gemma 3 1B wins 0.

Which is cheaper to run?

Neither model has a hosted API on OpenRouter, so you would run both yourself. Both need about 1.3 GB of memory at 4-bit quantization.

Which has the longer context window?

Both have a 32K-token context window.

Can I use LFM2.5 1.2B Thinking and Gemma 3 1B commercially?

LFM2.5 1.2B Thinking is released under LFM Open License and Gemma 3 1B under Gemma. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.