LLM EXPLORER 60,958 MODELS INDEXED

Qwen3.8 Flash Next NVFP4 by Mia-AiLab

By Mia-AiLab · 3298 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next NVFP4 is an open-source language model by Mia-AiLab. Features: 92.7b LLM, VRAM: 106GB, License: apache-2.0.

  8-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Modelopt   Nvfp4   Qwen3.8   Qwen3 8 flash next   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Mia-AiLab/Qwen3.8-Flash-Next-NVFP4 

Qwen3.8 Flash Next NVFP4 Parameters and Internals

LLM NameQwen3.8 Flash Next NVFP4
Repository 🤗https://huggingface.co/Mia-AiLab/Qwen3.8-Flash-Next-NVFP4 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size92.7b
Required VRAM106 GB
Updated2026-09-13
MaintainerMia-AiLab
Model Typeqwen3_8_flash_next
Model Files  0.0 GB   0.0 GB   2.8 GB: 1-of-34   1.6 GB: 2-of-34   1.6 GB: 3-of-34   1.6 GB: 4-of-34   1.6 GB: 5-of-34   1.6 GB: 6-of-34   1.6 GB: 7-of-34   1.6 GB: 8-of-34   1.6 GB: 9-of-34   1.6 GB: 10-of-34   1.6 GB: 11-of-34   1.6 GB: 12-of-34   1.6 GB: 13-of-34   1.6 GB: 14-of-34   1.6 GB: 15-of-34   1.6 GB: 16-of-34   1.6 GB: 17-of-34   1.6 GB: 18-of-34   2.4 GB: 19-of-34   5.1 GB: 20-of-34   5.2 GB: 21-of-34   5.1 GB: 22-of-34   5.2 GB: 23-of-34   5.2 GB: 24-of-34   5.1 GB: 25-of-34   5.2 GB: 26-of-34   5.1 GB: 27-of-34   5.2 GB: 28-of-34   5.1 GB: 29-of-34   5.2 GB: 30-of-34   5.2 GB: 31-of-34   5.1 GB: 32-of-34   5.0 GB: 33-of-34   1.6 GB: 34-of-34   0.0 GB
Model ArchitectureQwen3_8FlashNextForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.12.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace