LLM EXPLORER 60,828 MODELS INDEXED

Garbage 9B by jeiku

By jeiku · 72 downloads
HF Repo ↗ Copy URL

Garbage 9B is an open-source language model by jeiku. Features: 9b LLM, VRAM: 17.9GB, Context: 32K, License: apache-2.0, Merged, LLM Explorer Score: 0.13, Arc: 63.7, HellaSwag: 83, MMLU: 64.2, 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 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
Updated2026-08-01
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
MetaMath Mistral Pro32K / 17.9 GB186
Peagle 9B32K / 18 GB82030
...onarch Neurotic 9B Passthrough32K / 17.9 GB820
Mistral 9B Instruct32K / 35.9 GB70
GML Mistral Merged V132K / 18 GB861
Bepis 9B32K / 18 GB1006
Mistral 9B Instruct V0.232K / 17.9 GB893
Notus TheTop 7B Passthrough32K / 18 GB50
...raAI Foredoomed 9B EXL 2.8 Bpw32K / 3.7 GB50
Note: green Score (e.g. "73.2") means that the model is better than jeiku/Garbage_9B.