A model is still running

A model is still running or downloading. Leaving will stop the current operation. Stay on this page to let it finish.

Skip to content
LocalAI.toolsBeta

Join the waitlist

Get an email when the new apps and model runs launch.

No account needed.

Compare models by task

Explore the tasks and models you’ll be able to compare side by side. Local comparisons are coming with the upgraded LocalAI Tools.

49 tasks
Browser

LLM · Chat & text

Ask questions, draft text, and summarize with large language models (LLMs).

7 models10 variants10 precision/device pairs34 configurations
Browser

Speech to text (ASR)

Turn spoken audio into text and timestamps.

8 models14 variants17 precision/device pairs75 configurations
Browser

Streaming speech to text (ASR)

Transcribe incoming audio incrementally for live captions and voice input.

1 model1 variant1 precision/device pair1 configuration
Browser

Translation (MT)

Translate text between languages on your device.

3 models6 variants11 precision/device pairs16 configurations
Browser

Document understanding (OCR)

Extract structured text from document images.

4 models14 variants6 precision/device pairs18 configurations
Browser

Background removal

Separate a foreground subject from its background.

6 models10 variants16 precision/device pairs40 configurations
Browser

Text to speech (TTS)

Generate spoken audio from text.

8 models8 variants12 precision/device pairs29 configurations
Browser

Image upscaling

Increase image resolution locally; the supported scale depends on the checkpoint.

1 model1 variant10 precision/device pairs10 configurations
Browser

Image understanding

Describe images and ask questions about what they show.

3 models9 variants5 precision/device pairs15 configurations
Browser

Interactive segmentation

Click a subject to generate a segmentation mask.

3 models8 variants12 precision/device pairs35 configurations
Browser

Image restoration

Reduce noise or blur, improve document lighting, or straighten pages with task-specific restoration models.

1 model1 variant2 precision/device pairs2 configurations
Browser

Audio watermarking

Embed a sixteen-bit message in speech audio. Watermarks do not prove authenticity or ownership.

1 model1 variant2 precision/device pairs2 configurations
Browser

Audio noise removal

Reduce background noise in speech recordings.

2 models3 variants2 precision/device pairs3 configurations
Browser

Word-level audio alignment

Align transcript words with their positions in an audio recording.

1 model1 variant2 precision/device pairs2 configurations
Browser

Speaker diarization

Identify speaker turns and build a speaker timeline.

1 model1 variant1 precision/device pair1 configuration
Browser

Text embeddings

Convert text into vectors for search and comparison.

9 models24 variants16 precision/device pairs179 configurations
Browser

Image embeddings & similarity

Represent images as vectors for similarity search and grouping.

1 model10 variants6 precision/device pairs27 configurations
Browser

Object detection

Find common objects in images and return labeled bounding boxes.

4 models14 variants16 precision/device pairs78 configurations
Browser

Image classification

Classify images using the checkpoint’s predefined categories.

1 model1 variant2 precision/device pairs2 configurations
Browser

Image segmentation

Label objects and regions in a scene with pixel masks.

3 models21 variants16 precision/device pairs79 configurations
Browser

Text reranking

Sort candidate passages by relevance to a query.

2 models3 variants14 precision/device pairs23 configurations
Browser

Token classification (NER)

Identify and label entities within text.

1 model3 variants12 precision/device pairs18 configurations
Browser

Depth estimation

Estimate relative depth from a single image.

1 model2 variants2 precision/device pairs4 configurations
Browser

Pose estimation

Locate body keypoints in images.

2 models7 variants10 precision/device pairs44 configurations
Browser

Face detection

Locate faces and facial keypoints in images.

1 model3 variants1 precision/device pair3 configurations
Browser

Hand landmarks

Locate hands and their landmarks in images.

1 model1 variant1 precision/device pair1 configuration
Browser

Audio classification

Explore vocal emotion predictions from audio.

2 models2 variants10 precision/device pairs11 configurations
Browser

Typed decisions

Ask structured questions about a text state.

3 models5 variants10 precision/device pairs18 configurations
Browser

Guided image matting

Refine a cutout from an image and a foreground/background/unknown trimap. Returns a soft alpha matte.

1 model3 variants4 precision/device pairs12 configurations
Browser

Text-guided image selection

Provide an image and a text description. Returns a mask selecting matching pixels.

1 model1 variant8 precision/device pairs8 configurations
Browser

Text-guided object detection

Provide an image and object descriptions. Returns matching labels, scores, and bounding boxes.

1 model1 variant12 precision/device pairs12 configurations
Browser

Image & text label matching

Provide an image and candidate text labels. Returns a matching score for each label.

2 models4 variants10 precision/device pairs16 configurations
Browser

Sentence relationship (NLI)

Provide a premise and a hypothesis. Returns entailment, contradiction, and neutral scores.

1 model2 variants12 precision/device pairs14 configurations
Browser

Personal information detection

Provide text. Returns labeled spans that may contain personal information; review before redaction.

1 model1 variant2 precision/device pairs2 configurations
Browser

Image captioning & vision tasks

Provide an image, a selected task, and any required text prompt. Returns task-specific text or regions.

1 model4 variants12 precision/device pairs24 configurations
Browser

Facial expression classification

Provide a clear face image. Returns visible-expression category scores, not verified emotions.

1 model1 variant14 precision/device pairs14 configurations
Browser

Text region detection

Locate text regions in an image and return boxes or polygons. Does not read the text.

2 models4 variants2 precision/device pairs8 configurations
Browser

Document layout detection

Locate headings, paragraphs, tables and illustrations in page images; return regions and reading order.

1 model1 variant1 precision/device pair1 configuration
Browser

Face & portrait parsing

Label facial and portrait parts such as skin, hair, eyes and clothing with pixel masks.

1 model1 variant5 precision/device pairs5 configurations
Browser

Sentiment analysis

Classify the sentiment of text and return category scores.

1 model1 variant14 precision/device pairs14 configurations
Browser

Toxicity detection

Score potentially toxic text. Predictions need review and depend on the supported language.

1 model1 variant12 precision/device pairs12 configurations
Browser

Code editing

Provide code and edit context; receive a proposed revised file.

1 model1 variant1 precision/device pair1 configuration
Browser

Text continuation

Continue a text prefix with a pretrained base model, rather than an instruction-following chat model.

2 models2 variants3 precision/device pairs4 configurations
Browser

Table classification

Predict labels for table rows using labeled examples.

1 model1 variant4 precision/device pairs4 configurations
Browser

Table regression

Predict numbers and quantiles for table rows using examples.

1 model1 variant4 precision/device pairs4 configurations
Browser

Music beat tracking

Find beats and downbeats in music for rhythm grids and editing.

1 model5 variants2 precision/device pairs10 configurations
Browser

Audio embeddings

Turn a recording into a numerical vector for sound similarity search and clustering.

1 model1 variant2 precision/device pairs2 configurations
Browser

Pose-conditioned motion

Generate short motion transitions between skeletal pose conditions; offline animation only.

1 model1 variant1 precision/device pair1 configuration
Browser

Optical flow

Estimate the direction and amount of motion between two frames.

1 model12 variants2 precision/device pairs20 configurations