LLM EXPLORER 66,420 MODELS INDEXED

Mellum2.1 12B A2.5B Thinking MTP by JetBrains

By JetBrains · 210 downloads
HF Repo ↗ Copy URL

Mellum2.1 12B A2.5B Thinking MTP is an open-source language model by JetBrains. Features: 12b LLM, VRAM: 24.3GB, Context: 128K, License: apache-2.0.

  Arxiv:2605.31268 Base model:finetune:jetbrains/... Base model:jetbrains/mellum2-1...   Conversational   En   Endpoints compatible   Mellum   Model-index   Mtp   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow
Model Card on HF 🤗: https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP 

Mellum2.1 12B A2.5B Thinking MTP Parameters and Internals

LLM NameMellum2.1 12B A2.5B Thinking MTP
Repository 🤗https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP 
Base Model(s)  JetBrains/Mellum2-12B-A2.5B-Base   JetBrains/Mellum2-12B-A2.5B-Base
Model Size12b
Required VRAM24.3 GB
Updated2026-11-02
MaintainerJetBrains
Model Typemellum
Model Files  5.0 GB: 1-of-5   5.0 GB: 2-of-5   5.0 GB: 3-of-5   5.0 GB: 4-of-5   4.3 GB: 5-of-5   0.9 GB
Supported Languagesen
Model ArchitectureMellumForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version5.8.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size98304

Best Alternatives to Mellum2.1 12B A2.5B Thinking MTP

Best Alternatives
Context / RAM
Downloads
Likes
Mellum2.1 12B A2.5B Thinking128K / 24.3 GB80399
Mellum2 12B A2.5B Thinking128K / 24.3 GB6221327
Mellum2 12B A2.5B Base128K / 24.3 GB1675323
...lum2.1 12B A2.5B Thinking OQ5e128K / 8.6 GB6492
Mellum2 12B A2.5B Instruct128K / 24.3 GB449882
...12B A2.5B Thinking Abliterated128K / 24.3 GB1270
...lum2.1 12B A2.5B Thinking OQ8e128K / 12.8 GB2551
...1 12B A2.5B Thinking Mlx Nvfp4128K / 6.8 GB1951
Mellum2 12B A2.5B Thinking128K / 24.3 GB331
...um2.1 12B A2.5B Thinking MXFP4128K / 7.1 GB471
Note: green Score (e.g. "73.2") means that the model is better than JetBrains/Mellum2.1-12B-A2.5B-Thinking-MTP.