Sequential Hidden Decoding 8B N8 Instruct is an open-source language model by tencent. Features: 8b LLM, VRAM: 25.1GB, Context: 128K, License: other, Instruction-Based, LLM Explorer Score: 0.23.
| LLM Name | Sequential Hidden Decoding 8B N8 Instruct |
| Repository 🤗 | https://huggingface.co/tencent/Sequential-Hidden-Decoding-8B-n8-Instruct |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 25.1 GB |
| Updated | 2026-08-08 |
| Maintainer | tencent |
| Model Type | qwen3_scale_seq |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Qwen3ScaleSeqForCausalLM |
| License | other |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.57.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |