LLM EXPLORER 62,939 MODELS INDEXED

Qwen3.8 Flash Next RAZOR 65B A6B E256of512 by Nickyang

By Nickyang · 48 downloads

Qwen3.8 Flash Next RAZOR 65B A6B E256of512 is an open-source language model by Nickyang. Features: 65b LLM, VRAM: 3.5GB, License: other, LLM Explorer Score: 0.29.

  Arxiv:2609.30465 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.8-flash-...   Conversational   Endpoints compatible   Expert-pruning   Image-text-to-text   Mixture-of-experts   Moe   Pruning   Qwen   Qwen4 exp   Razor   Region:us   Safetensors

Qwen3.8 Flash Next RAZOR 65B A6B E256of512 Parameters and Internals

LLM NameQwen3.8 Flash Next RAZOR 65B A6B E256of512
Repository πŸ€—https://huggingface.co/Nickyang/Qwen3.8-Flash-Next-RAZOR-65B-A6B-E256of512 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size65b
Required VRAM3.5 GB
Updated2026-10-04
MaintainerNickyang
Model Typeqwen4_exp
Model Files  3.7 GB   5.0 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.8 GB   4.1 GB   4.2 GB   3.8 GB   4.3 GB   3.6 GB   4.3 GB   3.5 GB   4.5 GB   4.3 GB   4.5 GB   4.2 GB   3.8 GB   4.3 GB   3.6 GB   4.3 GB   3.6 GB   4.2 GB   3.8 GB   4.3 GB
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Transformers Version5.8.0.dev0