LLM EXPLORER 67,808 MODELS INDEXED

Novius Crusta by EhsaasBawa16

By EhsaasBawa16 · 116 downloads

Novius Crusta is an open-source language model by EhsaasBawa16. Features: 3b LLM, VRAM: 6.2GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, Code Generating.

  4bit Base model:finetune:unsloth/qw... Base model:unsloth/qwen2.5-cod...   Codegen   Conversational   En   Endpoints compatible   Instruct   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Unsloth

Novius Crusta Parameters and Internals

LLM NameNovius Crusta
Repository πŸ€—https://huggingface.co/EhsaasBawa16/Novius-Crusta 
Base Model(s)  unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit   unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit
Model Size3b
Required VRAM6.2 GB
Updated2026-11-19
MaintainerEhsaasBawa16
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   1.2 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Generates CodeYes
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version5.17.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Novius Crusta

Best Alternatives
Context / RAM
Downloads
Likes
...wen2.5 Coder 3B Sql Doctor Mlx32K / 1.7 GB3621
Qwen Manim Animation 16bit32K / 6.2 GB190
...wen2.5 Coder 3B Instruct V13.132K / 6.2 GB930
...2.5 Coder 3B Instruct Bnb 4bit32K / 2 GB208158
Qwen2.5 Coder 3B Instruct 4bit32K / 1.7 GB16212
Qwen3b Lora Finetune32K / 6.2 GB91
Qwen3b Lora Finetune32K / 6.2 GB01
Qwen2.5 0.5 Bnb 4bit32K / 2 GB231
VibeThinker 3B128K / 6.2 GB52745806
VibeThinker 3B Heretic128K / 6.2 GB10164
Note: green Score (e.g. "73.2") means that the model is better than EhsaasBawa16/Novius-Crusta.