h2oai/h2o-lightning-4b
image-text-to-text model by h2oai
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
H2O-Lightning-4B is a 4B-parameter decision model from H2O.ai, built on Qwen/Qwen3.5-4B. It answers typed decision questions about a record (a document, a ticket, a policy, a conversation) and about images that come with the record (photos, screenshots, scanned documents, charts). It returns a probability for every option: How to run it (recommended setup first): standard-library shim (h2olightningshim.py) in front, reads each request two-way. Start it with bash h2o-lightning-4b/serve.sh (the default). It scores 206 of JevBench's 231 public items this way; see Measured and Two-way reading. JevBench and the Decision Index. TWOWAY=0 bash h2o-lightning-4b/serve.sh. It uses the prefix cache and serves more requests per second under load; it scores 202 of the 231 items. See Run it. One engine, both modes and Serving at scale. Try it in your browser: live demo on Hugging Face Spaces (text and images; built by the Hugging Face team and running on ZeroGPU). Other formats:…
Read the full model card ↗ · Preview checked 2026-10-28T18:06:58.250Z
Inside the original model card — Document outline
- H2O-Lightning-4B
- See it in action
- Measured
- Image calibration
- Run it
- Long inputs
- Tokenizer
- For benchmark maintainers: JevBench
- For benchmark maintainers: Decision Index
- Two-way reading (recommended)
- One engine, both modes
- Image references and the Box question
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
h2oai/h2o-lightning-4b is a image-text-to-text model repository published by h2oai on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 3,127
- Cumulative likes
- 76
- Hugging Face trending score
- 56
- Reported safetensors parameters
- 4,539,265,536
- Architecture
- Qwen3_5ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-02T19:19:51.000Z
- Last modified
- 2026-10-15T12:31:46.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.5-4B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-16T06:41:23.932Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.