Nyarin 4B is an open-source language model by Kasugan0. Features: 4b LLM, VRAM: 8.9GB, Context: 256K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.19.
| LLM Name | Nyarin 4B |
| Repository 🤗 | https://huggingface.co/Kasugan0/Nyarin-4B |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 8.9 GB |
| Updated | 2026-06-03 |
| Maintainer | Kasugan0 |
| Model Type | qwen3 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | zh en |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 4.55.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3 4B Instruct 2507 | 256K / 8.1 GB | 3109972 | 911 |
| FastContext 1.0 4B SFT | 256K / 8.1 GB | 5735 | 357 |
| Voho Saudi Chat 4B | 256K / 8 GB | 468 | 1 |
| Fable Traces | 256K / 8.1 GB | 342 | 210 |
| FastContext 1.0 4B RL | 256K / 8.1 GB | 4559 | 61 |
| Hades 4B Abliterated | 256K / 8.1 GB | 173 | 1 |
| Qwen3 4B Instruct 2507 FP8 | 256K / 5.2 GB | 1100744 | 78 |
| ...en3 4B Instruct 2507 Depressed | 256K / 8.1 GB | 215 | 1 |
| Qwen3 4B Cuad Extractor | 256K / 8.1 GB | 322 | 1 |
| Qwen Fine Tuned | 256K / 8 GB | 293 | 1 |