Mythos Nano is an open-source language model by marcosvpj. Features: 3b LLM, VRAM: 1.3GB, Context: 128K, License: mit, Quantized, LLM Explorer Score: 0.32.
| LLM Name | Mythos Nano |
| Repository 🤗 | https://huggingface.co/marcosvpj/Mythos-nano |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 1.3 GB |
| Updated | 2026-09-15 |
| Maintainer | marcosvpj |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | gguf|q2|q4_k|q5_k |
| Model Architecture | Qwen2ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 5.12.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mythos Nano | 128K / 1.3 GB | 31571 | 104 |
| VibeThinker 3B Heretic | 128K / 6.2 GB | 1016 | 4 |
| Kartik Kundli AI 3B V2.0 | 32K / 6.3 GB | 516 | 1 |
| TINY THINKER INSTRUCT | 32K / 6.2 GB | 1382 | 4 |
| Spyfood Brain V2 | 32K / 6.2 GB | 153 | 0 |
| Zenith 3B | 32K / 6.3 GB | 190 | 3 |
| Qwen2.5 3B Instruct Heretic | 32K / 6.2 GB | 565 | 1 |
| Coder GRPO 3B | 32K / 6.2 GB | 298 | 7 |
| OpenCogito | 32K / 6.2 GB | 779 | 0 |
| OpenCognito R1 | 32K / 6.1 GB | 655 | 0 |