LLM EXPLORER 60,062 MODELS INDEXED

Qwen3.6 27B Reasoning Distill Lora V1 by Ravionhf

By Ravionhf · 12 downloads
HF Repo ↗ Copy URL

Qwen3.6 27B Reasoning Distill Lora V1 is an open-source language model by Ravionhf. Features: 27b LLM, VRAM: 0.4GB, License: apache-2.0, LLM Explorer Score: 0.25.

  Adapter Base model:adapter:qwen/qwen3....   Base model:qwen/qwen3.6-27b Dataset:r0b0tlab/qwen3.8-max-g...   Distillation   Finetuned   Lora   Peft   Qlora   Reasoning   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Ravionhf/qwen3.6-27b-reasoning-distill-lora-v1 

Qwen3.6 27B Reasoning Distill Lora V1 Parameters and Internals

LLM NameQwen3.6 27B Reasoning Distill Lora V1
Repository 🤗https://huggingface.co/Ravionhf/qwen3.6-27b-reasoning-distill-lora-v1 
Base Model(s)  Qwen/Qwen3.6-27B   Qwen/Qwen3.6-27B
Model Size27b
Required VRAM0.4 GB
Updated2026-08-20
MaintainerRavionhf
Model Files  0.4 GB
Model ArchitectureAdapter
Licenseapache-2.0
Model Max Length262144
Is Biasednone
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesin_proj_a|out_proj|in_proj_z|in_proj_qkv|o_proj|k_proj|q_proj|v_proj|in_proj_b
LoRA Alpha64
LoRA Dropout0
R Param32
Errorsreplace

Best Alternatives to Qwen3.6 27B Reasoning Distill Lora V1

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 27B Finance LoRA0K / 0.2 GB91
...en3.8 27B Absolute Heresy LoRA0K / 0.3 GB274
...laude Opus Reasoning Distilled0K / 0.9 GB222
Qwen3.8 27B Code SE LoRA0K / 0.6 GB191
Candle Qwen38 27B Sft 1p0K / 0.9 GB171
H3 IR Qwen3.6 27B LoRA0K / 0.2 GB71
Schierling Qwen3.6 27B LoRA0K / 0.6 GB140
....8 27B Yes Man Uncensored LoRA0K / 0.9 GB281
... 27B Uncensored FP8 Cyber LoRA0K / 0.2 GB141
... 6 27B Chinese Xianxia Lora V20K / 0.2 GB1698
Note: green Score (e.g. "73.2") means that the model is better than Ravionhf/qwen3.6-27b-reasoning-distill-lora-v1.