LLM EXPLORER 63,636 MODELS INDEXED

Qwen3.8 27B Perplexing Pegasus NVFP4 by AveLabs

By AveLabs · 21 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B Perplexing Pegasus NVFP4 is an open-source language model by AveLabs. Features: 27b LLM, VRAM: 23.8GB, License: apache-2.0, LLM Explorer Score: 0.27.

Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   En   Endpoints compatible   Image-text-to-text   Modelopt   Multimodal   Nvfp4   Qwen3 5   Region:us   Safetensors   Sharded   Systemone   Tensorflow   Typed-decisions
Model Card on HF 🤗: https://huggingface.co/AveLabs/Qwen3.8-27B-Perplexing-Pegasus-NVFP4 

Qwen3.8 27B Perplexing Pegasus NVFP4 Parameters and Internals

LLM NameQwen3.8 27B Perplexing Pegasus NVFP4
Repository 🤗https://huggingface.co/AveLabs/Qwen3.8-27B-Perplexing-Pegasus-NVFP4 
Base Model(s)  Pplx Decider V1 27B   Qwen/Qwen3.8-27B   perplexity-ai/pplx-decider-v1-27b   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM23.8 GB
Updated2026-10-10
MaintainerAveLabs
Model Typeqwen3_5
Model Files  10.0 GB: 1-of-3   10.0 GB: 2-of-3   3.8 GB: 3-of-3
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.14.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|im_end|>
Errorsreplace

Best Alternatives to Qwen3.8 27B Perplexing Pegasus NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB823
Qwen3.8 27B NPU2256K /  GB2524
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB95131835
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.8 27B FP80K / 0.4 GB123157416
Note: green Score (e.g. "73.2") means that the model is better than AveLabs/Qwen3.8-27B-Perplexing-Pegasus-NVFP4.