LLM EXPLORER 65,695 MODELS INDEXED

Mellum2 12B A2.5B Thinking by mIn-MAXsystem-Htz

By mIn-MAXsystem-Htz · 33 downloads
HF Repo ↗ Copy URL

Mellum2 12B A2.5B Thinking is an open-source language model by mIn-MAXsystem-Htz. Features: 12b LLM, VRAM: 24.3GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.29.

  Arxiv:2605.31268   Conversational   En   Endpoints compatible   Eval-results   Mellum   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mIn-MAXsystem-Htz/Mellum2-12B-A2.5B-Thinking 

Mellum2 12B A2.5B Thinking Parameters and Internals

LLM NameMellum2 12B A2.5B Thinking
Repository 🤗https://huggingface.co/mIn-MAXsystem-Htz/Mellum2-12B-A2.5B-Thinking 
Model Size12b
Required VRAM24.3 GB
Updated2026-10-26
MaintainermIn-MAXsystem-Htz
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
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 12B A2.5B Thinking

Best Alternatives
Context / RAM
Downloads
Likes
Mellum2.1 12B A2.5B Thinking128K / 24.3 GB80399
Mellum2 12B A2.5B Thinking128K / 24.3 GB6221327
...lum2.1 12B A2.5B Thinking OQ5e128K / 8.6 GB6492
Mellum2 12B A2.5B Base128K / 24.3 GB1675323
Mellum2 12B A2.5B Instruct128K / 24.3 GB449882
...lum2.1 12B A2.5B Thinking OQ8e128K / 12.8 GB2551
...1 12B A2.5B Thinking Mlx Nvfp4128K / 6.8 GB1951
...um2.1 12B A2.5B Thinking MXFP4128K / 7.1 GB471
...llum2 12B A2.5B Thinking Mxfp4128K / 6.4 GB3011
...llum2 12B A2.5B Instruct Mxfp4128K / 6.4 GB1661
Note: green Score (e.g. "73.2") means that the model is better than mIn-MAXsystem-Htz/Mellum2-12B-A2.5B-Thinking.