Back to Explore

LFM2.5-VL-1.6B

Liquid AI·Released 2026-01-05

Related Models

LFM2.5-8B-A1B2026-05-28 LFM2 24B A2B2026-02-25 LiquidAI: LFM2-24B-A2B2026-02-25 LFM2.5-1.2B-Thinking2026-01-20 LiquidAI: LFM2.5-1.2B-Instruct (free)2026-01-20 LiquidAI: LFM2.5-1.2B-Thinking (free)2026-01-20 LFM2.5-1.2B-Instruct2026-01-05 LiquidAI: LFM2-2.6B2025-10-20

Performance

508

tokens/sec

Faster than 99% of models

1.15

seconds

Faster than 47% of models

1.15

seconds

Faster than 64% of models

Market Median

94 tok/s

438% faster

Median TTFT

1.11s

3% slower

Speed Comparison

LFM2 1.2B

532 tok/s+5%

LFM2.5-1.2B-Instruct

537 tok/s+6%

Granite 4.0 H Small

441 tok/s-13%

Benchmarks

MMLU-ProNot evaluated

GPQA Diamond

28.9%

HLE

5.1%

LiveCodeBenchNot evaluated

SciCode

3.0%

TerminalBench Hard

0.0%

MATH-500Not evaluated

AIMENot evaluated

AIME 2025Not evaluated

IFBench

33.1%

Long Context Recall

0.0%

Tau2

8.5%

Market AverageTop Score

Quick Compare

Similar Models

Gemma 3 1B Instruct

Google

Gemma 3n E2B Instruct

Google

Granite 4.0 350M

IBM

Granite 4.0 H 350M

IBM

Tiny Aya Global

Cohere

Qwen3 0.6B (Non-reasoning)

Alibaba

Compare all 7 models