Fox 1.6 is an open-source language model by Fox-AI-by-teolm30. Features: 2b LLM, VRAM: 4GB, Context: 40K, License: apache-2.0, Quantized.
| LLM Name | Fox 1.6 |
| Repository π€ | https://huggingface.co/Fox-AI-by-teolm30/fox-1.6 |
| Model Size | 2b |
| Required VRAM | 4 GB |
| Updated | 2026-11-19 |
| Maintainer | Fox-AI-by-teolm30 |
| Model Type | qwen3 |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.51.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Math Model | 40K / 0 GB | 8 | 0 |
| Nous 1 2B | 40K / 3.4 GB | 353 | 2 |
| Apollo 1 2B | 40K / 3.4 GB | 119 | 5 |
| Nous 1 2B | 40K / 3.4 GB | 57 | 2 |
| Apollo 1 2B | 40K / 3.4 GB | 29 | 5 |
| Wolf Rayet 2B Prime3 | 40K / 3.4 GB | 12 | 0 |
| Puro 2B Base | 4K / 4.1 GB | 849 | 11 |