LLM EXPLORER 60,277 MODELS INDEXED

Qwen3.8 27B W4A16 GPTQ by ThakiCloud

By ThakiCloud · 23 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B W4A16 GPTQ is an open-source language model by ThakiCloud. Features: 27b LLM, VRAM: 18.6GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.28.

Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Compressed-tensors   Conversational   Edge   En   Gptq   Ko   Quantized   Qwen3 5   Region:us   Safetensors   Vllm   W4a16
Model Card on HF 🤗: https://huggingface.co/ThakiCloud/Qwen3.8-27B-W4A16-GPTQ 

Qwen3.8 27B W4A16 GPTQ Parameters and Internals

LLM NameQwen3.8 27B W4A16 GPTQ
Repository 🤗https://huggingface.co/ThakiCloud/Qwen3.8-27B-W4A16-GPTQ 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM18.6 GB
Updated2026-09-03
MaintainerThakiCloud
Model Typeqwen3_5
Model Files  18.6 GB
Supported Languagesen ko
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.16.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B W4A16 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B GPTQ Pro 4bit0K / 18.8 GB41540739
Qwen3.8 27B GPTQ INT4 FP8KV0K / 20.2 GB64882
...en3.8 27B W4A16 AutoRound GPTQ0K / 19.2 GB37485
Qwen3.5 27B GPTQ Int40K / 30.1 GB10538157
Qwen3.8 27B GPTQ 4bit0K / 21 GB24335
Qwen3.8 27B GPTQ Int40K / 20.2 GB22673
Qwen3.8 27B GPTQ INT4 G320K / 21 GB20893
...PTQ Int4 Sym G128 MTP BF16 B700K / 19.6 GB1781
Qwen3.8 27B GPTQ INT4 G1280K / 19.6 GB8733
Qwen3.8 27B GPTQ Int40K / 19.6 GB8811
Note: green Score (e.g. "73.2") means that the model is better than ThakiCloud/Qwen3.8-27B-W4A16-GPTQ.