LLM EXPLORER 58,975 MODELS INDEXED

Qwen3.8 27B GPTQ INT8 MTP by shawnw3i

By shawnw3i · 125 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B GPTQ INT8 MTP is an open-source language model by shawnw3i. Features: 27b LLM, VRAM: 36.2GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.3.

  8-bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   Endpoints compatible   Gptq   Image-text-to-text   Mtp   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Uncensored   Vllm
Model Card on HF 🤗: https://huggingface.co/shawnw3i/Qwen3.8-27B-GPTQ-INT8-MTP 

Qwen3.8 27B GPTQ INT8 MTP Parameters and Internals

LLM NameQwen3.8 27B GPTQ INT8 MTP
Repository 🤗https://huggingface.co/shawnw3i/Qwen3.8-27B-GPTQ-INT8-MTP 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM36.2 GB
Updated2026-08-19
Maintainershawnw3i
Model Typeqwen3_5
Model Files  3.1 GB: 1-of-12   3.1 GB: 2-of-12   3.1 GB: 3-of-12   3.2 GB: 4-of-12   3.2 GB: 5-of-12   3.1 GB: 6-of-12   3.2 GB: 7-of-12   3.2 GB: 8-of-12   3.1 GB: 9-of-12   2.9 GB: 10-of-12   2.5 GB: 11-of-12   2.5 GB: 12-of-12   0.8 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.15.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen3.8 27B GPTQ INT8 MTP

Best Alternatives
Context / RAM
Downloads
Likes
...en3.8 27B W4A16 AutoRound GPTQ0K / 19.2 GB37485
Qwen3.6 27B GPTQ Pro 4bit0K / 18.8 GB41540739
Qwen3.8 27B GPTQ Int40K / 20.2 GB22673
Qwen3.8 27B GPTQ 4bit0K / 21 GB24335
...7B GPTQ Int4 Sym G128 MTP BF160K / 19.6 GB5363
Qwen3.8 27B GPTQ Int40K / 19.6 GB8811
Qwen3.5 27B GPTQ Int40K / 30.1 GB10538157
Qwen3.8 27B GPTQ INT4 G1280K / 19.6 GB1423
Qwen3.8 27B GPTQ W4A160K / 0.8 GB1263
Qwen3.8 27B GPTQ INT4 G320K / 21 GB493
Note: green Score (e.g. "73.2") means that the model is better than shawnw3i/Qwen3.8-27B-GPTQ-INT8-MTP.