LLM EXPLORER 59,962 MODELS INDEXED

Qwen3.8 Flash Next AWQ INT4 by cyankiwi

By cyankiwi · 455 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next AWQ INT4 is an open-source language model by cyankiwi. Features: 78.6b LLM, VRAM: 188.8GB, License: other, Quantized, LLM Explorer Score: 0.37.

  Awq Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Compressed-tensors   Conversational   Endpoints compatible   Image-text-to-text   Quantized   Qwen4 exp   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cyankiwi/Qwen3.8-Flash-Next-AWQ-INT4 

Qwen3.8 Flash Next AWQ INT4 Parameters and Internals

LLM NameQwen3.8 Flash Next AWQ INT4
Repository 🤗https://huggingface.co/cyankiwi/Qwen3.8-Flash-Next-AWQ-INT4 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size78.6b
Required VRAM188.8 GB
Updated2026-08-30
Maintainercyankiwi
Model Typeqwen4_exp
Model Files  5.4 GB: 1-of-38   5.3 GB: 2-of-38   4.8 GB: 3-of-38   4.8 GB: 4-of-38   4.8 GB: 5-of-38   4.8 GB: 6-of-38   4.8 GB: 7-of-38   4.8 GB: 8-of-38   4.8 GB: 9-of-38   4.8 GB: 10-of-38   4.8 GB: 11-of-38   4.8 GB: 12-of-38   4.8 GB: 13-of-38   4.8 GB: 14-of-38   4.8 GB: 15-of-38   4.8 GB: 16-of-38   4.8 GB: 17-of-38   4.8 GB: 18-of-38   4.8 GB: 19-of-38   4.8 GB: 20-of-38   4.8 GB: 21-of-38   4.8 GB: 22-of-38   5.4 GB: 23-of-38   5.4 GB: 24-of-38   5.4 GB: 25-of-38   5.4 GB: 26-of-38   5.4 GB: 27-of-38   5.4 GB: 28-of-38   5.4 GB: 29-of-38   5.4 GB: 30-of-38   5.4 GB: 31-of-38   5.4 GB: 32-of-38   5.4 GB: 33-of-38   5.4 GB: 34-of-38   5.4 GB: 35-of-38   5.4 GB: 36-of-38   3.0 GB: 37-of-38   3.5 GB: 38-of-38
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace