LLM EXPLORER 60,897 MODELS INDEXED

Qwen3.8 27B GPTQ Int4 Sym G128 MTP BF16 by mikeinnyc

By mikeinnyc · 322 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B GPTQ Int4 Sym G128 MTP BF16 is an open-source language model by mikeinnyc. Features: 27b LLM, VRAM: 19.6GB, License: apache-2.0, Quantized.

  4-bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   Endpoints compatible   G128   Gptq   Image-text-to-text   Int4   Intel   Intel-arc   Intel-arc-pro   Long-context   Mtp   Quantized   Qwen   Qwen3.8   Qwen3 5   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow   Vllm   Xpu
Model Card on HF 🤗: https://huggingface.co/mikeinnyc/Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16 

Qwen3.8 27B GPTQ Int4 Sym G128 MTP BF16 Parameters and Internals

LLM NameQwen3.8 27B GPTQ Int4 Sym G128 MTP BF16
Repository 🤗https://huggingface.co/mikeinnyc/Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM19.6 GB
Updated2026-09-12
Maintainermikeinnyc
Model Typeqwen3_5
Model Files  3.5 GB: 1-of-5   4.3 GB: 2-of-5   4.3 GB: 3-of-5   4.3 GB: 4-of-5   3.2 GB: 5-of-5
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.15.0
Tokenizer ClassQwen2TokenizerFast
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B GPTQ Int4 Sym G128 MTP BF16

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B GPTQ Pro 4bit0K / 18.8 GB41540739
Qwen3.8 27B GPTQ INT4 FP8KV0K / 20.2 GB64882
Qwen3.5 27B GPTQ Int40K / 30.1 GB10538157
...en3.8 27B W4A16 AutoRound GPTQ0K / 19.2 GB37485
Qwen3.8 27B GPTQ 4bit0K / 21 GB24335
Qwen3.8 27B GPTQ INT4 G1280K / 19.6 GB23943
Qwen3.8 27B GPTQ Int40K / 20.2 GB22673
Qwen3.8 27B GPTQ INT4 G320K / 21 GB22003
Qwen3.8 27B GPTQ Int40K / 19.6 GB8811
Qwen3.8 27B GPTQ INT80K / 31.9 GB7612
Note: green Score (e.g. "73.2") means that the model is better than mikeinnyc/Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16.