Sintra AI
Home
Live Feed
Automation Hub
Prompt Library256
AI News554
Weekly Digest
Topic Hubs
AI History
AI Labs
Research
Learning Paths
Guides
Resources
Concepts
Videos
AI Tools74
Models
Claude
Google AI
Cost Calc
All tools/🎬 Video Generation

Marlin-2B

NemoStation

Free

2B video model — dense captions and plain-English timestamp search

About

Marlin-2B is a 2-billion-parameter video VLM fine-tuned on Qwen3.5-2B, purpose-built for two tasks developers actually need: dense captioning (what happened + when, structured with second-precise timestamps) and natural-language temporal grounding (query with plain English, get exact start/end timestamps back). At ~4–5 GB, it fits a 6 GB consumer GPU, beats Qwen2.5-VL-7B by +6.4 mIoU on TimeLens-Bench, and matches Gemini-2.0-Flash on temporal grounding. **Step-by-step:** 1) `pip install transformers`. 2) `from transformers import AutoModelForCausalLM, AutoProcessor`. 3) Load: `AutoModelForCausalLM.from_pretrained('NemoStation/Marlin-2B', trust_remote_code=True)`. 4) Call `.caption(video_path)` for dense timestamps or `.find(video_path, 'your query')` for NL search. **Best for:** video indexing, security/event detection, meeting search, sports highlights.

★
Key differentiator

Query any video in plain English and get back precise start/end timestamps.

Free (open-source on Hugging Face) · ~4–5 GB VRAM

video analysistimestampstemporal groundingopen-source2B params
Open Marlin-2B

More Video Generation tools

Runway

Leading AI video generation platform trusted by professional filmmakers

Freemium

Sora

OpenAI's text-to-video model generating cinematic clips up to 60 seconds

Paid

Kling AI

Kuaishou's high-quality video generation with up to 2-minute clips

Freemium