LLM EXPLORER 66,613 MODELS INDEXED

Qwen3.8 Flash Next W4A8 INT4 PLE by bradharrison

By bradharrison · 50 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next W4A8 INT4 PLE is an open-source language model by bradharrison. Features: 128.8b LLM, VRAM: 75.1GB, License: other.

  4-bit   Amd Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   Endpoints compatible   Gptq   Image-text-to-text   Ple   Quantized   Qwen4 exp   Region:us   Safetensors   Sharded   Tensorflow   W4a8
Model Card on HF 🤗: https://huggingface.co/bradharrison/Qwen3.8-Flash-Next-W4A8-INT4-PLE 

Qwen3.8 Flash Next W4A8 INT4 PLE Parameters and Internals

LLM NameQwen3.8 Flash Next W4A8 INT4 PLE
Repository 🤗https://huggingface.co/bradharrison/Qwen3.8-Flash-Next-W4A8-INT4-PLE 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size128.8b
Required VRAM75.1 GB
Updated2026-11-04
Maintainerbradharrison
Model Typeqwen4_exp
Model Files  2.2 GB: 1-of-20   4.3 GB: 3-of-20   4.3 GB: 4-of-20   4.3 GB: 5-of-20   4.3 GB: 6-of-20   4.3 GB: 7-of-20   4.3 GB: 8-of-20   4.3 GB: 9-of-20   4.3 GB: 10-of-20   4.3 GB: 11-of-20   4.3 GB: 12-of-20   4.3 GB: 13-of-20   4.3 GB: 14-of-20   4.3 GB: 15-of-20   4.3 GB: 16-of-20   4.3 GB: 17-of-20   3.2 GB: 18-of-20   3.4 GB: 19-of-20   1.8 GB: 20-of-20
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.20.2
Tokenizer ClassQwen2TokenizerFast
Padding Token<|endoftext|>
Errorsreplace