apple/FastVLM-0.5B
apple/FastVLM-0.5B is a apple record on this register. The Hugging Face model API lists the pipeline tag as text-generation. The safetensors index gives an exact parameter count of 758,833,760. Architectural context length (max_position_embeddings) is 32,768. The listed licence is apple-amlr. The Hub repository was created on 25 Aug 2025, which is the release date this register uses.
Primary source: the Hugging Face model card for apple/FastVLM-0.5B. Fields below come from that card, the Hub model API, and the repository’s own config.json when those files exist. A field we cannot source is omitted rather than guessed.
| Organisation | apple |
|---|---|
| ReleasedRepo creation date on Hugging Face | 25 Aug 2025 |
| Last modified | 3 Sept 2025 |
| ParametersExact, from the safetensors index | 759M 758,833,760 |
| Context lengthmax_position_embeddings — architectural maximum, not necessarily served | 32K 32,768 |
| Licence | apple-amlr |
| Pipeline / taskpipeline_tag on the Hugging Face model API | text-generation |
| File formats | safetensors |
| Architecture | llava_qwen2 |
| Layers | 24 |
| Vocabulary | 151,936 |
| DownloadsAt last check | 5.3k |
| Likes | 405 |
| Gated | No |
How to run
Safetensors weights are on the Hugging Face repository. The parameter count on this page came from that index.
Load it from huggingface.co/apple/FastVLM-0.5B. This page does not add install steps that the Hub files do not state.
Agent capabilities
Derived from the model’s own chat template, with the match counts behind each finding.
- ○Tool callingno evidence in template
- ○Reasoning / thinkingno evidence in template
- ●System prompt1 match in template
- ○Image inputno evidence in template
- ○Video inputno evidence in template
- ○Audio inputno evidence in template
Questions this record can answer
- When was FastVLM-0.5B released?
- The Hugging Face repository was created on 25 Aug 2025, which is the date this register uses.
- How many parameters does FastVLM-0.5B have?
- The safetensors index gives 758,833,760 parameters, shown here as 759M. That figure is exact, not rounded.
- What is the context length of FastVLM-0.5B?
- 32,768 tokens. That is max_position_embeddings from the model's own config.json — the architectural maximum, not necessarily the context a provider serves.
- What licence is FastVLM-0.5B under?
- The Hub card lists apple-amlr.
- Is FastVLM-0.5B gated?
- No. The Hugging Face model API does not mark this repository as gated.
- Does the FastVLM-0.5B chat template show tool calling?
- The chat template was read and no tool-calling evidence was found.
Where each field came from
- Hugging Face model API — releasedAt, lastModified, downloads, likes, task, license, gated, parameters. Checked 6 Oct 2026.
- config.json — contextLength, layers, vocabSize, architecture. Checked 6 Oct 2026.
- chat template — capabilities. Checked 6 Oct 2026.
First recorded 5 Oct 2026, last checked 6 Oct 2026. This record is compiled automatically from the sources above. Where a field is blank, we could not source it and have not guessed. Canonical repository: huggingface.co/apple/FastVLM-0.5B.