LLM EXPLORER 61,652 MODELS INDEXED

Qwen3.8 Flash Next INT4 Mixed AutoRound by Minachist

By Minachist · 260 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next INT4 Mixed AutoRound is an open-source language model by Minachist. Features: 139.7b LLM, VRAM: 155.7GB, License: other, LLM Explorer Score: 0.35.

  Auto-round Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Compressed-tensors   Conversational   Image-text-to-text   Int4   Int6   Qwen4 exp   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Minachist/Qwen3.8-Flash-Next-INT4-Mixed-AutoRound 

Qwen3.8 Flash Next INT4 Mixed AutoRound Parameters and Internals

LLM NameQwen3.8 Flash Next INT4 Mixed AutoRound
Repository 🤗https://huggingface.co/Minachist/Qwen3.8-Flash-Next-INT4-Mixed-AutoRound 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size139.7b
Required VRAM155.7 GB
Updated2026-09-19
MaintainerMinachist
Model Typeqwen4_exp
Model Files  3.8 GB: 1-of-14   5.0 GB: 2-of-14   5.0 GB: 3-of-14   5.0 GB: 4-of-14   5.0 GB: 5-of-14   5.0 GB: 6-of-14   5.0 GB: 7-of-14   5.0 GB: 8-of-14   5.0 GB: 9-of-14   5.0 GB: 10-of-14   5.0 GB: 11-of-14   5.0 GB: 12-of-14   5.0 GB: 13-of-14   3.9 GB: 14-of-14   1.6 GB: 1-of-33   3.2 GB: 2-of-33   3.2 GB: 3-of-33   3.2 GB: 4-of-33   3.2 GB: 5-of-33   3.2 GB: 6-of-33   3.2 GB: 7-of-33   3.2 GB: 8-of-33   3.2 GB: 9-of-33   3.2 GB: 10-of-33   3.2 GB: 11-of-33   3.2 GB: 12-of-33   3.2 GB: 13-of-33   3.2 GB: 14-of-33   3.2 GB: 15-of-33   3.2 GB: 16-of-33   3.2 GB: 17-of-33   3.2 GB: 18-of-33   3.2 GB: 19-of-33   3.2 GB: 20-of-33   3.2 GB: 21-of-33   3.2 GB: 22-of-33   3.2 GB: 23-of-33   3.2 GB: 24-of-33   3.2 GB: 25-of-33   3.2 GB: 26-of-33   3.2 GB: 27-of-33   3.2 GB: 28-of-33
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Transformers Version5.18.0.dev0