LLM EXPLORER 64,561 MODELS INDEXED

Qwen3.8 27B MixedInt4 AutoRound by Pilcothink

By Pilcothink · 2857 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B MixedInt4 AutoRound is an open-source language model by Pilcothink. Features: 27b LLM, VRAM: 20.4GB, LLM Explorer Score: 0.3.

  4-bit   Auto-round   Autoround Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   Endpoints compatible   Image-text-to-text   Int4   Mixed-precision   Quantized   Qwen   Qwen3.8   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/Pilcothink/Qwen3.8-27B-MixedInt4-AutoRound 

Qwen3.8 27B MixedInt4 AutoRound Parameters and Internals

LLM NameQwen3.8 27B MixedInt4 AutoRound
Repository 🤗https://huggingface.co/Pilcothink/Qwen3.8-27B-MixedInt4-AutoRound 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM20.4 GB
Updated2026-08-16
MaintainerPilcothink
Model Typeqwen3_5
Model Files  3.2 GB: 1-of-7   3.2 GB: 2-of-7   3.2 GB: 3-of-7   3.2 GB: 4-of-7   2.6 GB: 5-of-7   2.5 GB: 6-of-7   2.5 GB: 7-of-7   0.3 GB
Model ArchitectureQwen3_5ForConditionalGeneration
Model Max Length262144
Transformers Version5.15.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B MixedInt4 AutoRound

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 Pilcothink/Qwen3.8-27B-MixedInt4-AutoRound.