LLM EXPLORER 60,783 MODELS INDEXED

NEPALI LLM by shivam9980

By shivam9980 · 13 downloads
HF Repo ↗ Copy URL

NEPALI LLM is an open-source language model by shivam9980. Features: 9b LLM, VRAM: 20.5GB, Context: 8K, License: apache-2.0, Quantized, LLM Explorer Score: 0.16.

  4bit Base model:finetune:unsloth/ge... Base model:unsloth/gemma-2-9b-...   Dataset:uonlp/culturax   Endpoints compatible   Gemma2   Ne   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/shivam9980/NEPALI-LLM 

NEPALI LLM Parameters and Internals

Model Type 
text-generation-inference, transformers
Additional Notes 
This gemma2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameNEPALI LLM
Repository 🤗https://huggingface.co/shivam9980/NEPALI-LLM 
Base Model(s)  Gemma 2 9B Bnb 4bit   unsloth/gemma-2-9b-bnb-4bit
Model Size9b
Required VRAM20.5 GB
Updated2026-07-23
Maintainershivam9980
Model Typegemma2
Model Files  4.9 GB: 1-of-5   5.0 GB: 2-of-5   4.9 GB: 3-of-5   3.8 GB: 4-of-5   1.9 GB: 5-of-5
Supported Languagesne
Quantization Type4bit
Model ArchitectureGemma2ForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.44.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size271903
Torch Data Typebfloat16

Best Alternatives to NEPALI LLM

Best Alternatives
Context / RAM
Downloads
Likes
GWQ 9B Preview8K / 18.6 GB93
Gemma 2 9B 8bit8K / 9.8 GB1789
Gemma 2 9B 4bit8K / 5.2 GB1602
Gemma 2 9B It Bnb 4bit8K / 6.1 GB1300732
SASTRI 1 9B8K / 6.1 GB70
Gemma 2 9B Bnb 4bit8K / 6.1 GB1060531
Gemma 2 9B It Finance8K / 18.6 GB50
Athena Gemma 2 2B It8K / 23.8 GB02
Gemma 2 9B It 4bit8K / 5.2 GB169601
Gemma 2 9B It Ko RAG Bnb 4bit8K / 6.1 GB1550
Note: green Score (e.g. "73.2") means that the model is better than shivam9980/NEPALI-LLM.