LLM EXPLORER 66,383 MODELS INDEXED

Mellum2.1 12B A2.5B Thinking 6bit by mlx-community

By mlx-community · 616 downloads
HF Repo ↗ Copy URL

Mellum2.1 12B A2.5B Thinking 6bit is an open-source language model by mlx-community. Features: 12b LLM, VRAM: 9.9GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.3.

  6-bit   6bit Base model:jetbrains/mellum2.1... Base model:quantized:jetbrains...   Coding   Conversational   En   Mellum   Mlx   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Thinking
Model Card on HF 🤗: https://huggingface.co/mlx-community/Mellum2.1-12B-A2.5B-Thinking-6bit 

Mellum2.1 12B A2.5B Thinking 6bit Parameters and Internals

LLM NameMellum2.1 12B A2.5B Thinking 6bit
Repository 🤗https://huggingface.co/mlx-community/Mellum2.1-12B-A2.5B-Thinking-6bit 
Base Model(s)  JetBrains/Mellum2.1-12B-A2.5B-Thinking   JetBrains/Mellum2.1-12B-A2.5B-Thinking
Model Size12b
Required VRAM9.9 GB
Updated2026-10-22
Maintainermlx-community
Model Typemellum
Model Files  5.3 GB: 1-of-2   4.6 GB: 2-of-2
Supported Languagesen
Quantization Type6bit
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 6bit

Best Alternatives
Context / RAM
Downloads
Likes
...ellum2 12B A2.5B Thinking 4bit128K / 6.8 GB1261
...m2 12B A2.5B Thinking Mlx 4bit128K / 7.3 GB5215
...ellum2 12B A2.5B Instruct 4bit128K / 6.8 GB141
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
...12B A2.5B Thinking Abliterated128K / 24.3 GB1270
...lum2.1 12B A2.5B Thinking OQ8e128K / 12.8 GB2551
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Mellum2.1-12B-A2.5B-Thinking-6bit.