HoldMy4BKTO is an open-source language model by hardlyworking. Features: 4b LLM, VRAM: 8.8GB, Context: 256K, License: cc-by-nc-4.0, Instruction-Based, LLM Explorer Score: 0.18.
| LLM Name | HoldMy4BKTO |
| Repository 🤗 | https://huggingface.co/hardlyworking/HoldMy4BKTO |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 8.8 GB |
| Updated | 2026-05-16 |
| Maintainer | hardlyworking |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 4.52.3 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 102400 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Xgen Small 4B Instruct R | 256K / 17.7 GB | 54 | 4 |
| Aura 4B | 128K / 9 GB | 44 | 14 |
| Hamanasu Magnum 4B | 128K / 9 GB | 13 | 4 |
| Hamanasu Adventure 4B | 128K / 9.1 GB | 16 | 3 |
| Hamanasu 4B Chat Brainrot | 128K / 9 GB | 18 | 4 |
| Hamanasu 4B Instruct KTO V2 | 128K / 9 GB | 20 | 2 |
| Hamanasu 4B Instruct KTO V1 | 128K / 9 GB | 12 | 2 |
| Hamanasu 4B Instruct | 128K / 9 GB | 11 | 2 |
| 4B Inst | 128K / 9 GB | 16 | 0 |
| 4B Inst | 128K / 9 GB | 9 | 0 |