Hunyuan 1.8B Pretrain is an open-source language model by tencent. Features: 1.8b LLM, VRAM: 3.6GB, Context: 256K, LLM Explorer Score: 0.2.
| LLM Name | Hunyuan 1.8B Pretrain |
| Repository π€ | https://huggingface.co/tencent/Hunyuan-1.8B-Pretrain |
| Model Size | 1.8b |
| Required VRAM | 3.6 GB |
| Updated | 2026-08-08 |
| Maintainer | tencent |
| Model Type | hunyuan_v1_dense |
| Model Files | |
| Model Architecture | HunYuanDenseV1ForCausalLM |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 4.52.4 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <ο½hy_βpadβο½> |
| Vocabulary Size | 120818 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Hy MT2 1.8B | 256K / 4.1 GB | 22767 | 1131 |
| HY MT1.5 1.8B | 256K / 4.1 GB | 32205 | 1184 |
| Hy MT2 1.8B Heretic | 256K / 3.6 GB | 13 | 2 |
| Hunyuan 1.8B Instruct | 256K / 3.6 GB | 272 | 602 |
| HY MT1.5 1.8B 8bit | 256K / 1.9 GB | 576 | 5 |
| HY MT1.5 1.8B 4bit | 256K / 1 GB | 56 | 3 |
| ...unyuan 1.8B Instruct GPTQ Int4 | 256K / 1.3 GB | 42 | 1 |
| Hunyuan 1.8B Instruct AWQ Int4 | 256K / 1.3 GB | 28 | 3 |