What are the hardware requirements for Nethena 20B Glued?

Nethena 20B Glued requires approximately 39.9 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nethena 20B Glued and how large is it?

Nethena 20B Glued is developed by athirdpath, a model with 20b 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 Nethena 20B Glued?

Nethena 20B Glued is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nethena 20B Glued by athirdpath — VRAM 39.9GB, 4K context

Name: Nethena 20B Glued
Author: athirdpath

Nethena 20B Glued is an open-source language model by athirdpath. Features: 20b LLM, VRAM: 39.9GB, Context: 4K, License: cc-by-nc-4.0, LLM Explorer Score: 0.11.

Endpoints compatible Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/athirdpath/Nethena-20b-Glued

Nethena 20B Glued Benchmarks

LLME Score: 0.11115

^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)

Nethena 20B Glued (athirdpath/Nethena-20b-Glued)

🌟 Advertise your project 🚀

Nethena 20B Glued Parameters and Internals

Model Type

NSFW-oriented, Unaligned

Use Cases

Areas:

Role-playing, Medical advice, Narrative generation

Additional Notes

Test to explore 'gluing' components for improvements. Uses a private dataset.

Training Details

Data Sources:

Private dataset, Alpaca formatted dataset

Data Volume:

~500k tokens

Methodology:

LORA applied with 128 rank, 'gluing' components to reduce errors

Context Length:

2048

LLM Name	Nethena 20B Glued
Repository 🤗	https://huggingface.co/athirdpath/Nethena-20b-Glued
Model Size	20b
Required VRAM	39.9 GB
Updated	2026-05-24
Maintainer	athirdpath
Model Type	llama
Model Files	9.9 GB: 1-of-5 9.9 GB: 2-of-5 9.9 GB: 3-of-5 9.9 GB: 4-of-5 0.3 GB: 5-of-5
Model Architecture	LlamaForCausalLM
License	cc-by-nc-4.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.34.1
Tokenizer Class	LlamaTokenizer
Padding Token	[PAD]
Vocabulary Size	32001
Torch Data Type	float16

Quantized Models of the Nethena 20B Glued

Model	Likes	Downloads	VRAM
Nethena 20B Glued GGUF	3	119	8 GB
Nethena 20B Glued AWQ	2	11	10 GB
Nethena 20B Glued GPTQ	1	5	10 GB

Best Alternatives to Nethena 20B Glued

Best Alternatives	Context / RAM	Downloads	Likes
Internlm2 5 20B Llamafied	256K / 39.9 GB	1658	5
Stellaris Internlm2 20B R512	32K / 39.8 GB	9	3
Internlm2 Chat 20B Llama Old	32K / 39.6 GB	62	3
Internlm2 Base 20B Llama	32K / 39.6 GB	7	3
Internlm2 Base 20B Llama	32K / 39.6 GB	6	0
Internlm2 20B Llama	32K / 39.6 GB	200	20
Deita 20B	32K / 39.8 GB	63	1
Bagel 20B V04 Llama	32K / 39.6 GB	10	7
Bagel DPO 20B V04 Llama	32K / 39.6 GB	18	3
Internlm2 Limarp Chat 20B	32K / 39.6 GB	11	3

Note: green Score (e.g. "73.2") means that the model is better than athirdpath/Nethena-20b-Glued.

Rank the Nethena 20B Glued 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? 53972 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

Nethena 20B Glued by athirdpath