LLM EXPLORER 59,694 MODELS INDEXED

SuperQwen3.8 Abliterated 100 Fp8 by Jiunsong

By Jiunsong · 18 downloads
HF Repo ↗ Copy URL

SuperQwen3.8 Abliterated 100 Fp8 is an open-source language model by Jiunsong. Features: 27b LLM, VRAM: 30.5GB, License: apache-2.0, LLM Explorer Score: 0.28.

  Abliterated Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.8-27b   Compressed-tensors   Conversational   En   Endpoints compatible   Fp8   H100   H200   Image-text-to-text   Ko   Long-context   Multimodal   Obliteratus   Qwen3.5   Qwen3.8   Qwen3 5   Reasoning   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow   Tool-calling   Uncensored   Vllm   W8a8
Model Card on HF 🤗: https://huggingface.co/Jiunsong/SuperQwen3.8-abliterated-100-fp8 

SuperQwen3.8 Abliterated 100 Fp8 Parameters and Internals

LLM NameSuperQwen3.8 Abliterated 100 Fp8
Repository 🤗https://huggingface.co/Jiunsong/SuperQwen3.8-abliterated-100-fp8 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM30.5 GB
Updated2026-08-27
MaintainerJiunsong
Model Typeqwen3_5
Model Files  2.5 GB: 1-of-7   5.0 GB: 2-of-7   4.9 GB: 3-of-7   5.0 GB: 4-of-7   5.0 GB: 5-of-7   5.0 GB: 6-of-7   3.1 GB: 7-of-7   0.8 GB
Supported Languagesen ko
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.13.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to SuperQwen3.8 Abliterated 100 Fp8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.6 27B NVFP40K / 22 GB1887525419
Qwen3.6 27B FP80K / 0.4 GB7740472342
ThinkingCap Qwen3.6 27B0K / 54.7 GB35947614
Qwen3.5 27B0K / 55.2 GB25362941028
Qwen3.5 27B0K / 55.2 GB811516
Note: green Score (e.g. "73.2") means that the model is better than Jiunsong/SuperQwen3.8-abliterated-100-fp8.