What are the hardware requirements for Mellum2 12B A2.5B Thinking?

Mellum2 12B A2.5B Thinking requires approximately 24.3 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 Thinking and how large is it?

Mellum2 12B A2.5B Thinking is developed by JetBrains, 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 Thinking?

Mellum2 12B A2.5B Thinking 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 Thinking by JetBrains — VRAM 24.3GB, 128K context

Name: Mellum2 12B A2.5B Thinking
Author: JetBrains

Mellum2 12B A2.5B Thinking is an open-source language model by JetBrains. Features: 12b LLM, VRAM: 24.3GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.51.

Arxiv:2605.31268 Conversational En Endpoints compatible Eval-results Mellum Model-index Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/JetBrains/Mellum2-12B-A2.5B-Thinking

Mellum2 12B A2.5B Thinking Benchmarks

LLME Score: 0.51101

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Mellum2 12B A2.5B Thinking (JetBrains/Mellum2-12B-A2.5B-Thinking)

🌟 Advertise your project 🚀

Mellum2 12B A2.5B Thinking Parameters and Internals

LLM Name	Mellum2 12B A2.5B Thinking
Repository 🤗	https://huggingface.co/JetBrains/Mellum2-12B-A2.5B-Thinking
Model Size	12b
Required VRAM	24.3 GB
Updated	2026-06-03
Maintainer	JetBrains
Model Type	mellum
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 Languages	en
Model Architecture	MellumForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	5.8.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	98304

Quantized Models of the Mellum2 12B A2.5B Thinking

Model	Likes	Downloads	VRAM
...m2 12B A2.5B Thinking Mlx 4bit	2	163	7 GB

Best Alternatives to Mellum2 12B A2.5B Thinking

Best Alternatives	Context / RAM	Downloads	Likes
...m2 12B A2.5B Thinking Mlx 4bit	128K / 7.3 GB	163	2

Rank the Mellum2 12B A2.5B Thinking Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 54253 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Mellum2 12B A2.5B Thinking by JetBrains