LFM2.5-VL-1.6B
Liquid AI · LiquidAI/LFM2.5-VL-1.6B
Weights license: Publisher terms: LFM Open License v1.0 · code and components may use other terms
Quality
No comparable score
We track no public, comparable benchmark that covers this model yet. No score is inferred.
Reported by the publisher
- MMStar
- 50.67VLMEvalKit
- MM-IFEval
- 52.29VLMEvalKit
- BLINK
- 48.82VLMEvalKit
- InfoVQA (Val)
- 62.71VLMEvalKit
- OCRBench (v2)
- 41.44VLMEvalKit
- RealWorldQA
- 64.84VLMEvalKit
- MMMU (Val)
- 40.56VLMEvalKit
- MMMB (avg)
- 76.96VLMEvalKit
Every reported result
- Multilingual MMBench (avg)
- 65.90VLMEvalKit
Values as printed on the card, with the publisher's own settings (card section: 📊 Performance); column “LFM2.5-VL-1.6B”. Not comparable across publishers and not used in any ranking. Model card
Runs on
Fast memory holds it 119
The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.
Show all 119
Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.
Liquid AI released LFM2.5-VL-1.6B on 2026-01-05: a vision-language model that answers about images, with 1.6B parameters on the Hugging Face count and the Publisher terms: LFM Open License v1.0 license. Languages the publisher declares: en, ja, ko, fr, es, de, ar, zh.
License: commercial use allowed with conditions: Commercial use only while annual revenue is under USD 10M. At Q4 the weights load about 1.2 GB before each machine's reserve; image resolution, video frames and context add memory, and the vision encoder needs support in the runtime you pick.
Measured speed
No published measurement for this checkpoint
Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.
How to run
Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.
Library in source: transformers
Documented ways to run it
Copied as printed in the linked source (read 2026-10-18); not run by this site.
pip install transformers pillowfrom transformers import AutoProcessor, AutoModelForImageTextToText
from transformers.image_utils import load_image
# Load model and processor
model_id = "LiquidAI/LFM2.5-VL-1.6B"
model = AutoModelForImageTextToText.from_pretrained(
model_id,
device_map="auto",
dtype="bfloat16"
)
processor = AutoProcessor.from_pretrained(model_id)
# Load image and create conversation
url = "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
image = load_image(url)
conversation = [
{
"role": "user",
"content": [
{"type": "image", "image": image},
{"type": "text", "text": "What is in this image?"},
],
},
]
# Generate Answer
inputs = processor.apply_chat_template(
conversation,
add_generation_prompt=True,
return_tensors="pt",
return_dict=True,
tokenize=True,
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=64)
processor.batch_decode(outputs, skip_special_tokens=True)[0]
# This image showcases the iconic Statue of Liberty standing majestically on Liberty Island in New York Harbor. The statue is positioned on a small island surrounded by calm blue waters, with the New York City skyline visible in the background.Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / source
- LiquidAI/LFM2.5-VL-1.6B
- Task
- image-text-to-text
- Architecture
- Lfm2VlForConditionalGeneration
- Library in source
- transformers
- Weight license
- Publisher terms: LFM Open License v1.0LiquidAI/LFM2.5-VL-1.6B LICENSE: LFM Open License v1.0 (Hugging Face) · read 2026-10-19source
- Commercial use
- Allowed with conditions Commercial use only while annual revenue is under USD 10M · LFM Open License v1.0 (LiquidAI/LFM2-VL-1.6B LICENSE) · read 2026-10-18license text
- Languages
- en, ja, ko, fr, es, de, ar, zhModel card metadata · read 2026-10-25source
- Released
- Introducing LFM2.5: The Next Generation of On-Device AI | Blog | Liquid AI (publisher announcement; meta article:published_time) · read 2026-10-19source
Every stored field
- Revision checked
- 919fde3d022e3f90a4716006f993938ee8c2eb97
- Architecture
- Lfm2VlForConditionalGeneration
- Library
- transformers
- Hub task tag
- image-text-to-text
- Declared base models
- LiquidAI/LFM2.5-1.2B-Base
- Formats
- transformers, safetensors
- Access
- Open download
- Publisher kind
- Official
- Hub parameter count
- 1,596,625,904safetensors.total
- Repository created
- 2026-01-05creation is not the model's release
- Repository updated
- 2026-03-30a commit is not a release date
- Hub downloads (30 days) · likes
- 25,051 · 333this repository only · read 2026-10-25
- Read from the Hub page
- transformers class, task tagsHub overview and file listing · read 2026-10-18
- Catalog state
- Hub config or weights found; no inventory benchmark link
Sources
Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.
- Publisher model card
- License: LiquidAI/LFM2.5-VL-1.6B LICENSE: LFM Open License v1.0 (Hugging Face)
- Release date: Introducing LFM2.5: The Next Generation of On-Device AI | Blog | Liquid AI (publisher announcement; meta article:published_time)
Curated facts checked: 2026-10-19. The license and release date cite the publisher's sources; parameters, files and task come from the Hugging Face record, and memory is a labelled estimate from its parameter count. A value no source states stays empty; a repository commit is not a model release date.






























































