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

Garbage 9B by jeiku

 »  All LLMs  »  jeiku  »  Garbage 9B   URL Share it on

  93   

Garbage 9B is an open-source language model by jeiku. Features: 9b LLM, VRAM: 17.9GB, Context: 32K, License: apache-2.0, Merged, HF Score: 65.5, LLM Explorer Score: 0.14, Arc: 63.7, HellaSwag: 83, MMLU: 64.2, TruthfulQA: 47.9, WinoGrande: 80.4, GSM8K: 54.1.

  Merged Model Base model:chaoticneutrals/inf... Base model:finetune:chaoticneu... Dataset:resplendentai/luna alp...   En   Endpoints compatible   Lora   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/jeiku/Garbage_9B 

Garbage 9B Benchmarks

ARC: 63.65 vs 96.7 (so35)-34.2%
HellaSwag: 82.97 vs 95.3 (gpt4)-12.9%
MMLU: 64.18 vs 88.3 (so35)-27.3%
TruthfulQA: 47.87 vs 59 (gpt4)-18.9%
WinoGrande: 80.43 vs 87.5 (gpt4)-8.1%
GSM8K: 54.13 vs 96.4 (so35)-43.8%
LLME Score: 0.14376
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Garbage 9B (jeiku/Garbage_9B)
🌟 Advertise your project 🚀

Garbage 9B Parameters and Internals

Additional Notes 
The goal is to improve intelligence and RP ability beyond the 7B original models.
Supported Languages 
en (primary)
Training Details 
Data Sources:
ResplendentAI/Luna_Alpaca
Methodology:
This is a finetune of InfinityNexus_9B. This is my first time tuning a frankenmerge, so hopefully it works out.
LLM NameGarbage 9B
Repository 🤗https://huggingface.co/jeiku/Garbage_9B 
Base Model(s)  InfinityNexus 9B   jeiku/luna_lora_9B   ChaoticNeutrals/InfinityNexus_9B   jeiku/luna_lora_9B
Merged ModelYes
Model Size9b
Required VRAM17.9 GB
Updated2026-04-06
Maintainerjeiku
Model Typemistral
Model Files  9.9 GB: 1-of-2   8.0 GB: 2-of-2
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
LoRA ModelYes
Torch Data Typebfloat16

Best Alternatives to Garbage 9B

Best Alternatives
Context / RAM
Downloads
Likes
Peagle 9B32K / 18 GB128140
Peagle 9B32K / 18 GB124370
MetaMath Mistral Pro32K / 17.9 GB55
...onarch Neurotic 9B Passthrough32K / 17.9 GB80
GML Mistral Merged V132K / 18 GB7211
Mistral 9B Instruct32K / 35.9 GB70
Bepis 9B32K / 18 GB256
Mistral 9B Instruct V0.232K / 17.9 GB53
Notus TheTop 7B Passthrough32K / 18 GB50
MistralTrix V132K / 17.9 GB661110
Note: green Score (e.g. "73.2") means that the model is better than jeiku/Garbage_9B.

Rank the Garbage 9B 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? 52721 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