LLM EXPLORER 59,962 MODELS INDEXED

Qwen3.8 Flash Next Abliterated NVFP4 Plefp8 by gorbatjovy

By gorbatjovy · 118 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next Abliterated NVFP4 Plefp8 is an open-source language model by gorbatjovy. Features: 116.5b LLM, VRAM: 129GB, License: other, LLM Explorer Score: 0.3.

  8-bit   Abliterated Base model:quantized:windowsxp... Base model:windowsxp811203/qwe...   Conversational   Dgx-spark   Endpoints compatible   Flash-next   Fp4   Fp8   Image-text-to-text   Modelopt   Moe   Nvfp4   Qwen3.8   Qwen4 exp   Region:us   Safetensors   Sharded   Tensorflow   Uncensored   Vllm
Model Card on HF 🤗: https://huggingface.co/gorbatjovy/qwen3.8-flash-next-abliterated-NVFP4-plefp8 

Qwen3.8 Flash Next Abliterated NVFP4 Plefp8 Parameters and Internals

LLM NameQwen3.8 Flash Next Abliterated NVFP4 Plefp8
Repository 🤗https://huggingface.co/gorbatjovy/qwen3.8-flash-next-abliterated-NVFP4-plefp8 
Base Model(s)  windowsxp811203/Qwen3.8-Flash-Next-Abliterated-NVFP4   windowsxp811203/Qwen3.8-Flash-Next-Abliterated-NVFP4
Model Size116.5b
Required VRAM129 GB
Updated2026-08-30
Maintainergorbatjovy
Model Typeqwen4_exp
Model Files  10.0 GB: 1-of-9   10.0 GB: 2-of-9   10.0 GB: 3-of-9   10.0 GB: 4-of-9   10.0 GB: 5-of-9   10.0 GB: 6-of-9   10.0 GB: 7-of-9   7.8 GB: 9-of-9   6.1 GB: 10-of-10   6.4 GB: 0-of-8   6.4 GB: 1-of-8   6.4 GB: 2-of-8   6.4 GB: 3-of-8   6.4 GB: 4-of-8   6.4 GB: 5-of-8   6.4 GB: 6-of-8   6.4 GB: 7-of-8
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.16.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 Flash Next Abliterated NVFP4 Plefp8

Best Alternatives
Context / RAM
Downloads
Likes
...8 Flash Next Abliterated NVFP40K / 179.8 GB1153
Note: green Score (e.g. "73.2") means that the model is better than gorbatjovy/qwen3.8-flash-next-abliterated-NVFP4-plefp8.