ApX logoApX logo

LFM3 VL 2B

Parameters

2B

Context Length

128K

Modality

Text

Architecture

Dense

KV Cache Rate

48 KB/tok

License

other

Release Date

19 Oct 2026

Knowledge Cutoff

-

API Pricing (per 1M)

Self-hosted only

Hardware & System Requirements

Precision

Native

Context

Workload Memory: 3.81 GB

INT4 · 8K context

Base Weights: 0.93 GB

KV Cache: 0.38 GB

Runtime & Graphs: 2.50 GB

Minimum Required Hardware

1x NVIDIA L4 24GB

3.8 / 21.6 GB usable

1x RTX 3060 12GB

3.8 / 10.8 GB usable

Apple M4 24GB

3.8 / 18.0 GB usable

Determine requirements for your specific workload:

Open in VRAM Calculator

Runtime requirements

Checkpoint format

BF16

CUDA

>= 11.8

PyTorch

>= 2.1

Transformers

>= 5.19.0.dev0

ArchitecturePrecisionAttention kernel

Blackwell, Hopper

Native BF16

FlashAttention-3

Ada Lovelace, Ampere

Native BF16

FlashAttention-2

Architecture Diagram

Input TokensToken EmbeddingPosition: RoPEHidden: 2k · Context: 128K · Vocab: 128kx 24 layersRMSNormPre-AttentionGrouped-Query Attention16Q / 4KV heads · SW: 256Head dim: 128+RMSNormPre-FFNFeed-Forward NetworkSwiGLUIntermediate: 7.7k+Final RMSNormOutput Logits

Evaluation Benchmarks

No evaluation benchmarks for LFM3 VL 2B available.

Rankings

Overall Rank

-

Coding Rank

-

About LFM3 VL 2B

LFM3 VL 2B is an efficient vision-language model designed by Liquid AI for on-device multimodal reasoning and image understanding. It integrates visual encoders with the liquid foundational architecture to maximize inference efficiency.

Specifications

Attention

Attention Structure

Grouped-Query Attention

Attention Heads

16

Key-Value Heads

4

Attention Head Dimension

128

Position Embedding

ROPE

RoPE Theta

1,000,000

Sliding Window Attention

Yes

Sliding Window Size

256

Sliding Window Ratio

20.8%

Linear Attention

Yes

Linear Attention Ratio

54.2%

Normalization

RMS Normalization

Activation Function

SwigLU

Dimensions

Base Precision

BF16

Hidden Dimension Size

2,048

Number of Layers

24

FFN Intermediate Size (Dense)

7,680

Tokenizer

Vocabulary Size

128,000

About LFM3

The LFM3 model family developed by Liquid AI.


Other LFM3 Models
LFM3 VL 2B - VRAM Requirements, Specs & Benchmarks