LLM EXPLORER 63,407 MODELS INDEXED

Qwen3.8 Flash Next EXL3 4.05bpw by doth4580

By doth4580 · 5201 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next EXL3 4.05bpw is an open-source language model by doth4580. Features: 33.8b LLM, VRAM: 68GB, License: other, LLM Explorer Score: 0.34.

  4.05bpw Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   Dgx-spark   Exl3   Exllamav3   Image-text-to-text   Long-context   Moe   Qwen4 exp   Region:us   Safetensors   Sharded   Tensorflow   Trellis   Velogb10   Vision
Model Card on HF 🤗: https://huggingface.co/doth4580/Qwen3.8-Flash-Next-EXL3-4.05bpw 

Qwen3.8 Flash Next EXL3 4.05bpw Parameters and Internals

LLM NameQwen3.8 Flash Next EXL3 4.05bpw
Repository 🤗https://huggingface.co/doth4580/Qwen3.8-Flash-Next-EXL3-4.05bpw 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size33.8b
Required VRAM68 GB
Updated2026-10-08
Maintainerdoth4580
Model Typeqwen4_exp
Model Files  8.1 GB: 1-of-9   8.1 GB: 2-of-9   8.1 GB: 3-of-9   8.1 GB: 4-of-9   8.1 GB: 5-of-9   8.1 GB: 6-of-9   8.1 GB: 7-of-9   8.1 GB: 8-of-9   3.2 GB: 9-of-9   39.0 GB   0.6 GB   0.9 GB
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace