lfm3-vl

33 Downloads Updated an hour ago

LFM3-VL-2B is a vision-language model for on-device visual understanding.

vision tools thinking 2b

ollama run lfm3-vl

curl http://localhost:11434/api/chat \
  -d '{
    "model": "lfm3-vl",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='lfm3-vl',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'lfm3-vl',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model lfm3-vl

OpenCode

OpenCode ollama launch opencode --model lfm3-vl

Hermes Agent

Hermes Agent ollama launch hermes --model lfm3-vl

OpenClaw

OpenClaw ollama launch openclaw --model lfm3-vl

Models

Name

5 models

Size / Usage

Context

Input

lfm3-vl:latest

1.7GB · 125K context window · Text, Image · an hour ago

lfm3-vl:latest

1.7GB

125K

Text, Image

lfm3-vl:2b

1.7GB · 125K context window · Text, Image · an hour ago

lfm3-vl:2b latest

1.7GB

125K

Text, Image

Readme

LFM3-VL-2B is a vision-language model for on-device visual understanding. It takes text, images, and video (soon) as input, and combines the LFM3 language model with a new in-house vision encoder.

New in LFM3-VL-2B:

Video understanding (soon): the first LFM vision model that takes video as input. Ask questions about a recorded lecture, a walkthrough filmed on your phone, or a clip from a camera feed.
Thinking: the model reasons step by step before it answers. This helps most with harder visual questions, such as math, charts, and multi-step problems.
Spatial and embodied reasoning: the model finds objects and reasons about how they are placed relative to each other, a strong foundation for robotics applications.

Model details

The LFM3 family includes base, text, vision, audio, omni, and decision models.

Property	Specification
Checkpoint	Post-trained vision-language model
Parameters	1.92B: 1.73B language model, 164M vision encoder, 25M projector
Architecture	LFM3, 24 layers: 13 gated short convolutions, 5 sliding-window attention, 6 global attention
Vision encoder	14 layers: 8 gated depthwise 2D convolutions, 6 bidirectional attention, 16×16 patches with 2D rotary embeddings
Inputs	Text, images, and video (soon) at native resolution. Each 2×2 block of patches becomes one language token. Video is sampled at 2 fps.
Context length	128K tokens (input + output)
Vocabulary	128,000 tokens
Languages	English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, Polish
License	LFM Open License v1.0

LFM3-VL-2B is designed for on-device visual tasks: questions about video, reading documents, charts, and app screens, finding objects in an image, and spatial reasoning for robots. It is not recommended for coding, multi-turn conversations, or complex reasoning.

LFM3-VL-2B is a **vision-language model for on-device visual understanding.** It takes text, images, and video (soon) as input, and combines the LFM3 language model with a new in-house vision encoder.

New in LFM3-VL-2B:

* **Video understanding (soon):** the first LFM vision model that takes video as input. Ask questions about a recorded lecture, a walkthrough filmed on your phone, or a clip from a camera feed.
* **Thinking:** the model reasons step by step before it answers. This helps most with harder visual questions, such as math, charts, and multi-step problems.
* **Spatial and embodied reasoning:** the model finds objects and reasons about how they are placed relative to each other, a strong foundation for robotics applications.

# Model details
The LFM3 family includes base, text, vision, audio, omni, and decision models.

| Property | Specification |
|:--- |:---:|
| Checkpoint | Post-trained vision-language model |
| Parameters | 1.92B: 1.73B language model, 164M vision encoder, 25M projector |
| Architecture | LFM3, 24 layers: 13 gated short convolutions, 5 sliding-window attention, 6 global attention
| Vision encoder | 14 layers: 8 gated depthwise 2D convolutions, 6 bidirectional attention, 16×16 patches with 2D rotary embeddings
| Inputs | Text, images, and video (soon) at native resolution. Each 2×2 block of patches becomes one language token. Video is sampled at 2 fps.
| Context length|  128K tokens (input + output)
| Vocabulary |  128,000 tokens
| Languages |   English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, Polish
| License |   LFM Open License v1.0
LFM3-VL-2B is designed for on-device visual tasks: questions about video, reading documents, charts, and app screens, finding objects in an image, and spatial reasoning for robots. It is not recommended for coding, multi-turn conversations, or complex reasoning.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)