LLM EXPLORER 60,384 MODELS INDEXED

Qwen3.8 Flash Next NVFP4 PLE NVFP4 by provsalt

By provsalt · 1920 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next NVFP4 PLE NVFP4 is an open-source language model by provsalt. Features: 92.7b LLM, VRAM: 82.4GB, License: other, LLM Explorer Score: 0.33.

  8-bit Base model:inferact/qwen3.8-fl... Base model:quantized:inferact/...   Conversational   Custom-code   Image-text-to-text   Modelopt   Nvfp4   Qwen   Qwen3.8   Qwen4   Qwen4 exp   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/provsalt/Qwen3.8-Flash-Next-NVFP4-PLE-NVFP4 

Qwen3.8 Flash Next NVFP4 PLE NVFP4 Parameters and Internals

LLM NameQwen3.8 Flash Next NVFP4 PLE NVFP4
Repository 🤗https://huggingface.co/provsalt/Qwen3.8-Flash-Next-NVFP4-PLE-NVFP4 
Base Model(s)  Inferact/Qwen3.8-Flash-Next-NVFP4   Inferact/Qwen3.8-Flash-Next-NVFP4
Model Size92.7b
Required VRAM82.4 GB
Updated2026-09-04
Maintainerprovsalt
Model Typeqwen4_exp
Model Files  5.0 GB: 2-of-4   5.0 GB: 3-of-4   0.8 GB: 4-of-4   4.2 GB: 1-of-16   4.2 GB: 2-of-16   4.2 GB: 3-of-16   4.2 GB: 4-of-16   4.2 GB: 5-of-16   4.2 GB: 6-of-16   4.2 GB: 7-of-16   4.2 GB: 8-of-16   4.2 GB: 9-of-16   4.2 GB: 10-of-16   4.2 GB: 11-of-16   4.2 GB: 12-of-16   4.2 GB: 13-of-16   4.2 GB: 14-of-16   4.2 GB: 15-of-16   4.2 GB: 16-of-16   1.6 GB   0.2 GB: 1-of-128   0.2 GB: 2-of-128   0.2 GB: 3-of-128   0.2 GB: 4-of-128   0.2 GB: 5-of-128   0.2 GB: 6-of-128   0.2 GB: 7-of-128   0.2 GB: 8-of-128   0.2 GB: 9-of-128   0.2 GB: 10-of-128   0.2 GB: 11-of-128   0.2 GB: 12-of-128   0.2 GB: 13-of-128   0.2 GB: 14-of-128   0.2 GB: 15-of-128   0.2 GB: 16-of-128   0.2 GB: 17-of-128   0.2 GB: 18-of-128   0.2 GB: 19-of-128   0.2 GB: 20-of-128   0.2 GB: 21-of-128   0.2 GB: 22-of-128
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Transformers Version5.8.0.dev0