LLM EXPLORER 59,962 MODELS INDEXED

Qwen3.8 Flash Next MXFP4 FP8 by tcclaviger

By tcclaviger · 257 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next MXFP4 FP8 is an open-source language model by tcclaviger. Features: 187.5b LLM, VRAM: 55.1GB, License: apache-2.0, LLM Explorer Score: 0.34.

  8-bit   Amd Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Compressed-tensors   Conversational   Endpoints compatible   Image-text-to-text   Mxfp4   Qwen4 exp   R9700   Rdna4   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8 

Qwen3.8 Flash Next MXFP4 FP8 Parameters and Internals

LLM NameQwen3.8 Flash Next MXFP4 FP8
Repository 🤗https://huggingface.co/tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size187.5b
Required VRAM55.1 GB
Updated2026-08-30
Maintainertcclaviger
Model Typeqwen4_exp
Model Files  1.0 GB: 1-of-131   0.9 GB: 2-of-131   0.5 GB: 3-of-131   0.9 GB: 4-of-131   1.3 GB: 5-of-131   1.6 GB: 6-of-131   1.6 GB: 7-of-131   1.6 GB: 8-of-131   1.6 GB: 9-of-131   1.6 GB: 10-of-131   1.6 GB: 11-of-131   1.6 GB: 12-of-131   1.6 GB: 13-of-131   1.6 GB: 14-of-131   1.6 GB: 15-of-131   1.6 GB: 16-of-131   1.6 GB: 17-of-131   1.6 GB: 18-of-131   1.6 GB: 19-of-131   1.6 GB: 20-of-131   1.6 GB: 21-of-131   1.6 GB: 22-of-131   1.6 GB: 23-of-131   1.6 GB: 24-of-131   1.6 GB: 25-of-131   1.6 GB: 26-of-131   1.6 GB: 27-of-131   1.6 GB: 28-of-131   1.6 GB: 29-of-131   1.6 GB: 30-of-131   1.6 GB: 31-of-131   1.6 GB: 32-of-131   1.6 GB: 33-of-131   1.6 GB: 34-of-131   1.6 GB: 35-of-131   1.6 GB: 36-of-131   0.9 GB: 37-of-131
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseapache-2.0
Transformers Version5.8.0.dev0