What are the hardware requirements for Huginn 0125?

Huginn 0125 requires approximately 15.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Huginn 0125 and how large is it?

Huginn 0125 is developed by tomg-group-umd, a model with 3.9b 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 Huginn 0125?

Huginn 0125 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Huginn 0125 by tomg-group-umd — VRAM 15.6GB

Name: Huginn 0125
Author: tomg-group-umd

Huginn 0125 is an open-source language model by tomg-group-umd. Features: 3.9b LLM, VRAM: 15.6GB, License: apache-2.0, LLM Explorer Score: 0.21.

Arxiv:2502.05171 Code Conversational Custom code Dataset:tomg-group-umd/huginn-... En Huginn raven Math Reasoning Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/tomg-group-umd/huginn-0125

Huginn 0125 Parameters and Internals

LLM Name	Huginn 0125
Repository 🤗	https://huggingface.co/tomg-group-umd/huginn-0125
Model Size	3.9b
Required VRAM	15.6 GB
Updated	2026-10-22
Maintainer	tomg-group-umd
Model Type	huginn_raven
Model Files	4.8 GB: 1-of-4 4.7 GB: 2-of-4 4.7 GB: 3-of-4 1.4 GB: 4-of-4
Supported Languages	en
Model Architecture	RavenForCausalLM
License	apache-2.0
Transformers Version	4.44.2
Is Biased	0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|pad\|>
Vocabulary Size	65536
Torch Data Type	float32

Rank the Huginn 0125 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