LFM 2 1.2B is Liquid AI's language model. A compact 1.2B-parameter Liquid Foundation Model from the LFM2 family designed for efficient on-device and edge deployment.
Specifications
Canonical IDliquid-lfm-2-1-2b
TypeLanguage
StatusActive
CreatorLiquid AILiquid AI
Input ModalitiesText
Output ModalitiesText
Parameters1.2B
Benchmarks
Intelligence Index
#548
Math Index
#260
MMLU-Pro
#333
GPQA
#530
HLE
#336
LiveCodeBench
#331
IFBench
#409
Time to First Token
#181
SciCode
#521
AIME 2025
#260
LCR
#454
TerminalBench Hard
#394
TAU2
#378
Output TPS
#413

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Cheapest Instances to Run It

Cloud GPU instances that can host LFM 2 1.2B, ranked by cheapest on-demand price. The model needs about 3 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NV4as_v4AzureAMD Radeon Instinct MI2516 GB$0.233/hr
Standard_NV4ads_V710_v5AzureAMD Radeon Pro V710 (24GB)4 GB$0.333/hr
g5g.xlargeAWST4g16 GB$0.420/hr
7 more instances can run LFM 2 1.2B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
LFM 2 24B A2B128KAvailable
LFM 2.5 1.2B Instruct33KAvailable
LFM 2.5 1.2B Thinking33KAvailable
LFM 2 1.2BCurrent
LFM 2.5 8B A1BAvailable
LFM 2 2.6BAvailable
LFM 2 8B A1BAvailable
LFM 2.5 1.6B VLAvailable
LFM 2.5 2.6B Free66KAvailable
LFM 2.5 2.6B128KAvailable
LFM 40B131K$0.100$0.200Available

Model IDs

lfm2-1-2b
liquid-lfm-2-1-2b