LLM EXPLORER 60,587 MODELS INDEXED

Qwen3.8 27B Kearuga by 0xWhiteMage

By 0xWhiteMage · 782 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B Kearuga is an open-source language model by 0xWhiteMage. Features: 27b LLM, VRAM: 24GB, License: apache-2.0, LLM Explorer Score: 0.36.

Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   De   Dflash2   Dgx-spark   En   Endpoints compatible   Es   Fp8   Fr   Gb10   Gptq   Grace-blackwell   Hybrid-quantization   Image-text-to-text   Ja   Kearuga   Ko   Modelopt   Nvfp4   Qwen3   Qwen3.5   Qwen3 5   Region:us   Ru   Safetensors   Sharded   Sm121   Speculative-decoding   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/0xWhiteMage/Qwen3.8-27B-Kearuga 

Qwen3.8 27B Kearuga Parameters and Internals

LLM NameQwen3.8 27B Kearuga
Repository 🤗https://huggingface.co/0xWhiteMage/Qwen3.8-27B-Kearuga 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM24 GB
Updated2026-09-06
Maintainer0xWhiteMage
Model Typeqwen3_5
Model Files  9.4 GB: 1-of-3   10.0 GB: 2-of-3   4.6 GB: 3-of-3   0.8 GB
Supported Languagesen zh de fr ja ko es ru
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.12.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B Kearuga

Best Alternatives
Context / RAM
Downloads
Likes
Agens Pilot1024K / 54.7 GB1061
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.6 27B NVFP40K / 22 GB1887525419
Cortex Mini 1 Preview0K / 55.6 GB962
Qwen3.6 27B FP80K / 0.4 GB7740472342
Qwen3.5 27B0K / 55.2 GB25362941028
Note: green Score (e.g. "73.2") means that the model is better than 0xWhiteMage/Qwen3.8-27B-Kearuga.