What are the hardware requirements for Akins 3B?

Akins 3B requires approximately 5.6 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 Akins 3B and how large is it?

Akins 3B is developed by acrastt, a model with 3b 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 Akins 3B?

Akins 3B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Akins 3B by acrastt — VRAM 5.6GB, 4K context

Name: Akins 3B
Author: acrastt

Akins 3B is an open-source language model by acrastt. Features: 3b LLM, VRAM: 5.6GB, Context: 4K, License: cc-by-sa-4.0, LLM Explorer Score: 0.1.

Arxiv:2305.14314 Custom code Dataset:norquinal/claude multi... En Pytorch Region:us Safetensors Stablelm epoch

Model Card on HF 🤗: https://huggingface.co/acrastt/Akins-3B

Akins 3B Benchmarks

LLME Score: 0.09883

^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)

🌟 Advertise your project 🚀

Akins 3B Parameters and Internals

Model Type

text generation

Additional Notes

GGUF quantizations available [here](https://huggingface.co/TheBloke/Akins-3B-GGUF). GPTQ quantizations available [here](https://huggingface.co/TheBloke/Akins-3B-GPTQ).

Supported Languages

en (English)

Training Details

Data Sources:

Norquinal/claude_multiround_chat_1k

Methodology:

instruction-tuned with QLoRA

Training Time:

2 epochs

Input Output

Input Format:

USER: {prompt} ASSISTANT:

Accepted Modalities:

text

LLM Name	Akins 3B
Repository 🤗	https://huggingface.co/acrastt/Akins-3B
Model Size	3b
Required VRAM	5.6 GB
Updated	2026-05-23
Maintainer	acrastt
Model Type	stablelm_epoch
Model Files	5.6 GB 5.6 GB
Supported Languages	en
Model Architecture	StableLMEpochForCausalLM
License	cc-by-sa-4.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.0.dev0
Tokenizer Class	GPTNeoXTokenizerFast
Vocabulary Size	50304
Torch Data Type	float16

Quantized Models of the Akins 3B

Model	Likes	Downloads	VRAM
Akins 3B GGUF	8	393	1 GB
Akins 3B GPTQ	2	117	1 GB

Best Alternatives to Akins 3B

Best Alternatives	Context / RAM	Downloads	Likes
Stable Code 3B Mlx	16K / 5.6 GB	42	1
Aura 3B	4K / 5.6 GB	3	2
Slim Extract	4K / 5.6 GB	169	13
Slim Boolean	4K / 5.6 GB	11	4
Slim Tags 3B	4K / 5.6 GB	15	4
Slim Sa Ner	4K / 5.6 GB	3	6
Slim Summary	4K / 5.6 GB	13	8
Slim Xsum	4K / 5.6 GB	16	6
Tofu 3B	4K / 5.6 GB	8	2
Memphis CoT 3B	4K / 5.6 GB	23	31

Note: green Score (e.g. "73.2") means that the model is better than acrastt/Akins-3B.

Rank the Akins 3B 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? 53999 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

Akins 3B by acrastt