LLM EXPLORER 66,845 MODELS INDEXED

Qwen3.8 Flash Next EXL3 INT8 3.05bpw by kusuriya-labs

By kusuriya-labs · 23 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next EXL3 INT8 3.05bpw is an open-source language model by kusuriya-labs. Features: 26.2b LLM, VRAM: 52.3GB, License: other.

Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   Exl3   Exl3-int8   Image-text-to-text   Quantized   Qwen4 exp   Region:us   Rocm   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/kusuriya-labs/Qwen3.8-Flash-Next-EXL3-INT8-3.05bpw 

Qwen3.8 Flash Next EXL3 INT8 3.05bpw Parameters and Internals

LLM NameQwen3.8 Flash Next EXL3 INT8 3.05bpw
Repository 🤗https://huggingface.co/kusuriya-labs/Qwen3.8-Flash-Next-EXL3-INT8-3.05bpw 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size26.2b
Required VRAM52.3 GB
Updated2026-11-09
Maintainerkusuriya-labs
Model Typeqwen4_exp
Model Files  7.8 GB: 1-of-7   8.1 GB: 2-of-7   8.1 GB: 3-of-7   8.1 GB: 4-of-7   8.1 GB: 5-of-7   8.1 GB: 6-of-7   4.0 GB: 7-of-7   32.6 GB
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 Flash Next EXL3 INT8 3.05bpw

Best Alternatives
Context / RAM
Downloads
Likes
...lash Next Uncensored Exl3 3bpw0K / 52.3 GB2232
Note: green Score (e.g. "73.2") means that the model is better than kusuriya-labs/Qwen3.8-Flash-Next-EXL3-INT8-3.05bpw.