LLM EXPLORER 62,404 MODELS INDEXED

Qwen3.8 Flash Next EXL3 SAGE 4.15bpw by vcruz305

By vcruz305 · 41 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next EXL3 SAGE 4.15bpw is an open-source language model by vcruz305. Features: 34.9b LLM, VRAM: 69.9GB, License: other, LLM Explorer Score: 0.28.

  4-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   En   Exl3   Exllamav3   Image-text-to-text   Moe   Multimodal   Quantized   Qwen4 exp   Region:us   Safetensors   Sage   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/vcruz305/Qwen3.8-Flash-Next-EXL3-SAGE-4.15bpw 

Qwen3.8 Flash Next EXL3 SAGE 4.15bpw Parameters and Internals

LLM NameQwen3.8 Flash Next EXL3 SAGE 4.15bpw
Repository 🤗https://huggingface.co/vcruz305/Qwen3.8-Flash-Next-EXL3-SAGE-4.15bpw 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size34.9b
Required VRAM69.9 GB
Updated2026-09-28
Maintainervcruz305
Model Typeqwen4_exp
Model Files  7.5 GB: 1-of-9   6.8 GB: 2-of-9   7.5 GB: 3-of-9   7.7 GB: 4-of-9   7.7 GB: 5-of-9   8.2 GB: 6-of-9   8.4 GB: 7-of-9   7.9 GB: 8-of-9   8.2 GB: 9-of-9   39.0 GB
Supported Languagesen zh
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 SAGE 4.15bpw

Best Alternatives
Context / RAM
Downloads
Likes
...lash Next Uncensored Exl3 4bpw0K / 69.8 GB1971