What are the hardware requirements for Mellum 4B Base 4bit?

Mellum 4B Base 4bit requires approximately 2.3 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mellum 4B Base 4bit and how large is it?

Mellum 4B Base 4bit is developed by mlx-community, a model with 4b 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 Mellum 4B Base 4bit?

Mellum 4B Base 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mellum 4B Base 4bit by mlx-community — VRAM 2.3GB, 8K context

Name: Mellum 4B Base 4bit
Author: mlx-community

Mellum 4B Base 4bit is an open-source language model by mlx-community. Features: 4b LLM, VRAM: 2.3GB, Context: 8K, License: apache-2.0, Quantized, LLM Explorer Score: 0.19.

4-bit 4bit Base model:jetbrains/mellum-4b... Base model:quantized:jetbrains... Code Dataset:bigcode/commitpack Dataset:bigcode/starcoderdata Dataset:bigcode/the-stack Dataset:bigcode/the-stack-v2 Llama Mlx Model-index Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/mlx-community/Mellum-4b-base-4bit

Mellum 4B Base 4bit Parameters and Internals

LLM Name	Mellum 4B Base 4bit
Repository 🤗	https://huggingface.co/mlx-community/Mellum-4b-base-4bit
Base Model(s)	Mellum 4B Base JetBrains/Mellum-4b-base
Model Size	4b
Required VRAM	2.3 GB
Updated	2026-07-18
Maintainer	mlx-community
Model Type	llama
Model Files	2.3 GB
Quantization Type	4bit
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.51.3
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	98304
Torch Data Type	bfloat16
Errors	replace

Rank the Mellum 4B Base 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 Mellum 4B Base 4bit

Best Alternatives	Context / RAM	Downloads	Likes
...a3.2 ColdBrew 4B Discovery F16	128K / 7.2 GB	9	0
...Nemotron Nano 4B V1.1 Bnb 4bit	128K / 3.5 GB	218	0
... Nano 4B V1.1 Unsloth Bnb 4bit	128K / 3.5 GB	66	1
4Bcpt	256K / 8.8 GB	5	0
HoldMy4BKTO	256K / 8.8 GB	5	0
Xgen Small 4B Instruct R	256K / 17.7 GB	54	4
Xgen Small 4B Base R	256K / 17.7 GB	30	3
SJT 4B	146K / 7.6 GB	7	0
...lama 3.1 Nemotron Nano 4B V1.1	128K / 9 GB	3940	116
Nemotron W 4b MagLight 0.1	128K / 9.2 GB	9	3

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Mellum-4b-base-4bit.