LLM EXPLORER 64,561 MODELS INDEXED

Qwen3.8 27B Heretic Ara NVFP4 by PassingByPixels

By PassingByPixels · 172 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B Heretic Ara NVFP4 is an open-source language model by PassingByPixels. Features: 27b LLM, VRAM: 19.8GB, License: apache-2.0, LLM Explorer Score: 0.26.

  8-bit   Ara Base model:quantized:trohrbaug... Base model:trohrbaugh/qwen3.8-...   Blackwell   Conversational   Dgx-spark   En   Heretic   Image-text-to-text   Modelopt   Mtp   Nvfp4   Quantized   Qwen3.8   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/PassingByPixels/Qwen3.8-27B-heretic-ara-NVFP4 

Qwen3.8 27B Heretic Ara NVFP4 Parameters and Internals

LLM NameQwen3.8 27B Heretic Ara NVFP4
Repository 🤗https://huggingface.co/PassingByPixels/Qwen3.8-27B-heretic-ara-NVFP4 
Base Model(s)  trohrbaugh/Qwen3.8-27B-heretic-ara   trohrbaugh/Qwen3.8-27B-heretic-ara
Model Size27b
Required VRAM19.8 GB
Updated2026-08-18
MaintainerPassingByPixels
Model Typeqwen3_5
Model Files  10.0 GB: 1-of-2   9.8 GB: 2-of-2   0.8 GB
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.9.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|im_end|>
Errorsreplace

Best Alternatives to Qwen3.8 27B Heretic Ara NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB953
Qwen3.8 27B NPU2256K /  GB2524
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB201602194
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.6 27B NVFP40K / 22 GB1887525419
Note: green Score (e.g. "73.2") means that the model is better than PassingByPixels/Qwen3.8-27B-heretic-ara-NVFP4.