Tamed Sigma is an open-source language model by tinycompany. Features: 3.1b LLM, VRAM: 6.2GB, Context: 32K, License: mit, MoE, LLM Explorer Score: 0.16.
| LLM Name | Tamed Sigma |
| Repository 🤗 | https://huggingface.co/tinycompany/Tamed-Sigma |
| Model Size | 3.1b |
| Required VRAM | 6.2 GB |
| Updated | 2026-08-06 |
| Maintainer | tinycompany |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| License | mit |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 81920 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Saba Passthrough 2 | 128K / 6.2 GB | 7 | 0 |
| AetherSearch DPO | 32K / 6.2 GB | 724 | 1 |
| Arakandar | 32K / 6.2 GB | 160 | 1 |
| Augmented F96977dba6704cd1 | 32K / 6.2 GB | 91 | 0 |
| Tenun Fs0807 Parent 20260921 | 32K / 6.2 GB | 16 | 0 |
| OpenCognito R2 | 32K / 6.2 GB | 259 | 0 |
| Augmented 0defe3c8c8c799fb | 32K / 6.2 GB | 43 | 0 |
| Augmented 619958b5bf46bea2 | 32K / 6.2 GB | 9 | 0 |
| Legal Qwen India | 32K / 2.2 GB | 5 | 2 |
| TethysAI Vortex Reasoning | 32K / 6.2 GB | 11 | 0 |