The publication AI reads — a remote MCP server, nothing to install.Connect your agent →
Model register·microsoft

microsoft/FrogNano-4B-2609

microsoft/FrogNano-4B-2609 is a microsoft record on this register. The safetensors index gives an exact parameter count of 4,659,865,088. Architectural context length (max_position_embeddings) is 262,144. The listed licence is mit. The Hub repository was created on 17 Sept 2026, which is the release date this register uses.

Primary source: the Hugging Face model card for microsoft/FrogNano-4B-2609. 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.

Organisationmicrosoft
ReleasedRepo creation date on Hugging Face17 Sept 2026
Last modified2 Oct 2026
ParametersExact, from the safetensors index4.7B 4,659,865,088
Context lengthmax_position_embeddings — architectural maximum, not necessarily served256K 262,144
Licencemit
File formatssafetensors
Architectureqwen3_5
Layers32
Vocabulary248,320
DownloadsAt last check1.4k
Likes155
GatedNo

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/microsoft/FrogNano-4B-2609. 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 calling28 matches in template
  • ●Reasoning / thinking17 matches in template
  • ●System prompt3 matches in template
  • ●Image input4 matches in template
  • ●Video input4 matches in template
  • ○Audio inputno evidence in template

Questions this record can answer

When was FrogNano-4B-2609 released?
The Hugging Face repository was created on 17 Sept 2026, which is the date this register uses.
How many parameters does FrogNano-4B-2609 have?
The safetensors index gives 4,659,865,088 parameters, shown here as 4.7B. That figure is exact, not rounded.
What is the context length of FrogNano-4B-2609?
262,144 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 FrogNano-4B-2609 under?
The Hub card lists mit.
Is FrogNano-4B-2609 gated?
No. The Hugging Face model API does not mark this repository as gated.
Does the FrogNano-4B-2609 chat template show tool calling?
The chat template contains evidence of tool calling.

Where each field came from

  • Hugging Face model API — releasedAt, lastModified, downloads, likes, task, license, gated, parameters. Checked 12 Oct 2026.
  • config.json — contextLength, layers, vocabSize, architecture. Checked 12 Oct 2026.
  • chat template — capabilities. Checked 12 Oct 2026.

First recorded 3 Oct 2026, last checked 12 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/microsoft/FrogNano-4B-2609.