Nyarin 4B by Kasugan0

 ยป  All LLMs  ยป  Kasugan0  ยป  Nyarin 4B   URL Share it on

  Autotrain compatible Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-4b-instr...   Conversational   Dataset:liumindmind/nekoqa-10k   En   Endpoints compatible   Instruct   Qwen3   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF ๐Ÿค—: https://huggingface.co/Kasugan0/Nyarin-4B 

Nyarin 4B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nyarin 4B (Kasugan0/Nyarin-4B)
๐ŸŒŸ Advertise your project ๐Ÿš€

Nyarin 4B Parameters and Internals

LLM NameNyarin 4B
Repository ๐Ÿค—https://huggingface.co/Kasugan0/Nyarin-4B 
Base Model(s)  Qwen3 4B Instruct 2507   Qwen/Qwen3-4B-Instruct-2507
Model Size4b
Required VRAM8.9 GB
Updated2025-08-26
MaintainerKasugan0
Model Typeqwen3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   3.9 GB: 2-of-2   0.0 GB
Supported Languageszh en
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.55.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Nyarin 4B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B Instruct 2507256K / 8.1 GB442938237
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB1688925
Qwen3 4B Instruct 2507256K / 8.1 GB152957
...4B Thinking 2507 DAG Reasoning256K / 16.1 GB88044
... Instruct 2507 Gabliterated V1256K / 8.1 GB3777
... Instruct 2507 Gabliterated V2256K / 8.1 GB2456
...nstruct 2507 20250808 233922 0256K / 8.1 GB765
NOVER1 Qwen3 4B256K / 8.9 GB552
Qwen3 4B Instruct 2507 Imdb256K / 8.1 GB620
BingoGuard Qwen3 4B Pt256K / 8.1 GB530
Note: green Score (e.g. "73.2") means that the model is better than Kasugan0/Nyarin-4B.

Rank the Nyarin 4B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 50900 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124