JetBrains / Mellum2.1-12B-A2.5B-Thinking-MTP
Text Generation12B21014Updated Oct 30, 2026
Downloads
210
Likes
14
Last updated
Oct 30, 2026
License
apache-2.0
[!Note] This repository is Mellum2.1 Thinking with its multi-token prediction (MTP) head included. The model weights are byte-identical to that release; the head adds one shard and one config key. Use this repository for speculative decoding with vLLM 0.33 or newer and transf…
Tasks & library
- text generation
- transformers
Tags
- transformers
- mellum
- text-generation
- mtp
- speculative-decoding
- conversational
Technical specifications
Parameters12B
Librarytransformers
Languagesen
Base modelJetBrains/Mellum2-12B-A2.5B-Base
Licenseapache-2.0