LLM EXPLORER 58,297 MODELS INDEXED

Mellum2 12B A2.5B Instruct Mxfp4 by mlx-community

By mlx-community · 166 downloads
HF Repo ↗ Copy URL

Mellum2 12B A2.5B Instruct Mxfp4 is an open-source language model by mlx-community. Features: 12b LLM, VRAM: 6.4GB, Context: 128K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.31.

  4-bit Base model:jetbrains/mellum2-1... Base model:quantized:jetbrains...   Conversational   En   Instruct   Mellum   Mlx   Moe   Mxfp4   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Mellum2-12B-A2.5B-Instruct-mxfp4 

Mellum2 12B A2.5B Instruct Mxfp4 Parameters and Internals

LLM NameMellum2 12B A2.5B Instruct Mxfp4
Repository 🤗https://huggingface.co/mlx-community/Mellum2-12B-A2.5B-Instruct-mxfp4 
Base Model(s)  JetBrains/Mellum2-12B-A2.5B-Instruct   JetBrains/Mellum2-12B-A2.5B-Instruct
Model Size12b
Required VRAM6.4 GB
Updated2026-08-13
Maintainermlx-community
Model Typemellum
Instruction-BasedYes
Model Files  5.3 GB: 1-of-2   1.1 GB: 2-of-2
Supported Languagesen
Model ArchitectureMellumForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version5.8.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Vocabulary Size98304

Best Alternatives to Mellum2 12B A2.5B Instruct Mxfp4

Best Alternatives
Context / RAM
Downloads
Likes
Mellum2 12B A2.5B Instruct128K / 24.3 GB449882
...ellum2 12B A2.5B Instruct 4bit128K / 6.8 GB141
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Mellum2-12B-A2.5B-Instruct-mxfp4.