LLM EXPLORER 62,589 MODELS INDEXED

Qwen3.8 27B AWQ INT4 by derikn

By derikn · 35 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B AWQ INT4 is an open-source language model by derikn. Features: 27b LLM, VRAM: 18.6GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.29.

  4-bit   Auto-round   Awq Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   Dataset:neelnanda/pile-10k   Endpoints compatible   Image-text-to-text   Int4   Intel-arc   Mtp   Quantized   Qwen   Qwen3.8   Qwen3 5   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Thinking   Tool-calling   Vision   Vllm   Xpu
Model Card on HF 🤗: https://huggingface.co/derikn/Qwen3.8-27B-AWQ-INT4 

Qwen3.8 27B AWQ INT4 Parameters and Internals

LLM NameQwen3.8 27B AWQ INT4
Repository 🤗https://huggingface.co/derikn/Qwen3.8-27B-AWQ-INT4 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM18.6 GB
Updated2026-09-30
Maintainerderikn
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   0.8 GB: 5-of-7   2.5 GB: 6-of-7   2.5 GB: 7-of-7   0.8 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.17.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen3.8 27B AWQ INT4

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B AWQ INT40K / 20.4 GB2563390103
Qwen3.8 27B AWQ INT40K / 21 GB2101532
Swift 1.5 Qwen3.8 27B AWQ INT40K / 21 GB5505
Qwen3.6 27B AWQ0K / 22 GB66892424
Qwen3.6 27B AWQ BF16 INT40K / 28.3 GB41917141
...wen3.6 27B Abliterated AWQ MTP0K / 18.4 GB24497812
...ingCap Qwen3.8 27B NVFP4A4 AWQ0K / 22.5 GB22410
Qwen3.5 27B AWQ0K / 21.9 GB37092044
Qwen3.5 27B AWQ 4bit0K / 20 GB27906442
Qwen3.8 27B AWQ 4bit0K / 27.7 GB118746
Note: green Score (e.g. "73.2") means that the model is better than derikn/Qwen3.8-27B-AWQ-INT4.