What are the hardware requirements for Mellum2 12B A2.5B Instruct 4bit?

Mellum2 12B A2.5B Instruct 4bit requires approximately 6.8 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mellum2 12B A2.5B Instruct 4bit and how large is it?

Mellum2 12B A2.5B Instruct 4bit is developed by mlx-community, a model with 12b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Mellum2 12B A2.5B Instruct 4bit?

Mellum2 12B A2.5B Instruct 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mellum2 12B A2.5B Instruct 4bit by mlx-community — VRAM 6.8GB, 128K context

Name: Mellum2 12B A2.5B Instruct 4bit
Author: mlx-community

Mellum2 12B A2.5B Instruct 4bit is an open-source language model by mlx-community. Features: 12b LLM, VRAM: 6.8GB, Context: 128K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.28.

4-bit 4bit Base model:jetbrains/mellum2-1... Base model:quantized:jetbrains... Conversational En Instruct Mellum Mlx Moe Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Mellum2-12B-A2.5B-Instruct-4bit

Mellum2 12B A2.5B Instruct 4bit Parameters and Internals

LLM Name	Mellum2 12B A2.5B Instruct 4bit
Repository 🤗	https://huggingface.co/mlx-community/Mellum2-12B-A2.5B-Instruct-4bit
Base Model(s)	JetBrains/Mellum2-12B-A2.5B-Instruct JetBrains/Mellum2-12B-A2.5B-Instruct
Model Size	12b
Required VRAM	6.8 GB
Updated	2026-08-13
Maintainer	mlx-community
Model Type	mellum
Instruction-Based	Yes
Model Files	5.3 GB: 1-of-2 1.5 GB: 2-of-2
Supported Languages	en
Quantization Type	4bit
Model Architecture	MellumForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	5.8.1
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Vocabulary Size	98304

Rank the Mellum2 12B A2.5B Instruct 4bit capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Mellum2 12B A2.5B Instruct 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Mellum2 12B A2.5B Instruct	128K / 24.3 GB	4498	82
...llum2 12B A2.5B Instruct Mxfp4	128K / 6.4 GB	166	1

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Mellum2-12B-A2.5B-Instruct-4bit.