ShortThink Qwen3 1.7B SFT is an open-source language model by AmareshHebbar. Features: 1.7b LLM, VRAM: 3.5GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.31.
| LLM Name | ShortThink Qwen3 1.7B SFT |
| Repository π€ | https://huggingface.co/AmareshHebbar/ShortThink_Qwen3_1.7B_SFT |
| Base Model(s) | |
| Model Size | 1.7b |
| Required VRAM | 3.5 GB |
| Updated | 2026-11-18 |
| Maintainer | AmareshHebbar |
| Model Type | qwen3 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen3ForCausalLM |
| License | apache-2.0 |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.55.4 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Reaper Base | 128K / 3.4 GB | 393 | 0 |
| Lucy 128K | 128K / 3.4 GB | 123 | 112 |
| Polaris 1.7B Preview | 128K / 3.4 GB | 73 | 8 |
| DictaLM 3.0 1.7B Instruct | 60K / 3.4 GB | 2842 | 1 |
| Qwen3 1.7B | 40K / 4 GB | 5633291 | 500 |
| Dweep 1.7B | 40K / 3.5 GB | 181 | 1 |
| Qwen3 1.7B Eka Clinical Sft | 40K / 3.4 GB | 171 | 1 |
| Wolof Qwen3 1.7B V2610 | 40K / 3.4 GB | 133 | 1 |
| ShortThink Qwen3 1.7B DPO | 40K / 3.5 GB | 267 | 0 |
| ShortThink Qwen3 1.7B GRPO | 40K / 3.5 GB | 201 | 0 |