LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Akins 3B GGUF by TheBloke

 »  All LLMs  »  TheBloke  »  Akins 3B GGUF   URL Share it on

  107   
  Arxiv:2305.14314   Base model:acrastt/akins-3b Base model:quantized:acrastt/a... Dataset:norquinal/claude multi...   En   Gguf   Quantized   Region:us   Stablelm
Model Card on HF 🤗: https://huggingface.co/TheBloke/Akins-3B-GGUF 

Akins 3B GGUF Benchmarks

LLME Score: 0.12842
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Akins 3B GGUF (TheBloke/Akins-3B-GGUF)
🌟 Advertise your project 🚀

Akins 3B GGUF Parameters and Internals

Model Type 
stablelm, text-generation
Additional Notes 
Quantized by TheBloke using Massed Compute's hardware. Supports various quantization methods such as GGUF, Q2_K to Q8_0.
Supported Languages 
en (Proficient)
Training Details 
Data Sources:
Claude Multiround Chat 1K
Methodology:
Instruction tuned for 2 epochs with QLoRA (2305.14314)
Input Output 
Input Format:
USER: {prompt} ASSISTANT:
Accepted Modalities:
text
LLM NameAkins 3B GGUF
Repository 🤗https://huggingface.co/TheBloke/Akins-3B-GGUF 
Model NameAkins 3B
Model CreatorBohan Du
Base Model(s)  Akins 3B   acrastt/Akins-3B
Model Size3b
Required VRAM1.2 GB
Updated2025-07-30
MaintainerTheBloke
Model Typestablelm
Model Files  1.2 GB   1.5 GB   1.4 GB   1.2 GB   1.6 GB   1.7 GB   1.6 GB   1.9 GB   2.0 GB   1.9 GB   2.3 GB   3.0 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licensecc-by-sa-4.0

Best Alternatives to Akins 3B GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Llama32 3B En Emo V3128K / 2 GB60
Llama 3.2 3B VanRossum0K / 6.5 GB1020
Legal Llama3 Lora Model0K / 3.4 GB160
MedQwen3B Reasoner0K / 6.2 GB13413
Llama Chat Summary 3.2 3B GGUF0K / 2 GB2034
Llama Deepsync 3B GGUF0K / 2 GB834
...a Song Stream 3B Instruct GGUF0K / 2 GB1246
QwQ LCoT 3B Instruct GGUF0K / 1.9 GB647
Deepsync 240 GGUF0K / 2 GB122
... Sentient 3.2 3B Instruct GGUF0K / 2 GB1098
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Akins-3B-GGUF.

Rank the Akins 3B GGUF 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? 50230 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.
Release v20241124
  Support LLM Explorer