Candle Qwen38 27B Sft 1p is an open-source language model by moolm. Features: 27b LLM, VRAM: 0.9GB, License: apache-2.0, LLM Explorer Score: 0.25.
| LLM Name | Candle Qwen38 27B Sft 1p |
| Repository 🤗 | https://huggingface.co/moolm/candle-qwen38-27b-sft-1p |
| Base Model(s) | |
| Model Size | 27b |
| Required VRAM | 0.9 GB |
| Updated | 2026-08-18 |
| Maintainer | moolm |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Model Max Length | 262144 |
| Is Biased | none |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|endoftext|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | k_proj|down_proj|in_proj_a|in_proj_z|o_proj|gate_proj|v_proj|in_proj_qkv|out_proj|in_proj_b|up_proj|q_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0.05 |
| R Param | 32 |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3.8 27B Velocity | 0K / 0.9 GB | 83 | 1 |
| ...3.8 27B Abliterated Cyber LoRA | 0K / 0.4 GB | 22 | 1 |
| ...en3.8 27B Absolute Heresy LoRA | 0K / 0.3 GB | 27 | 4 |
| ...laude Opus Reasoning Distilled | 0K / 0.9 GB | 22 | 2 |
| Qwen3.8 27B Finance LoRA | 0K / 0.2 GB | 9 | 1 |
| Qwen3.8 27B Code SE LoRA | 0K / 0.6 GB | 19 | 1 |
| ... 27B Reasoning Distill Lora V1 | 0K / 0.4 GB | 12 | 0 |
| H3 IR Qwen3.6 27B LoRA | 0K / 0.2 GB | 7 | 1 |
| Schierling Qwen3.6 27B LoRA | 0K / 0.6 GB | 14 | 0 |
| Kairos Sophia 1.0 27B | 0K / 0.9 GB | 28 | 1 |