LLM EXPLORER 60,587 MODELS INDEXED

Qwen3.8 Flash Next NVFP4 PLE MMap MTP Spark by edougawa

By edougawa · 80 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next NVFP4 PLE MMap MTP Spark is an open-source language model by edougawa. Features: 73.2b LLM, VRAM: 3.4GB, License: other, LLM Explorer Score: 0.3.

  8-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   Dgx-spark   Gb10   Image-text-to-text   Modelopt   Mtp   Multimodal   Nvfp4   Quantized   Qwen4 exp   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/edougawa/Qwen3.8-Flash-Next-NVFP4-PLE-MMap-MTP-Spark 

Qwen3.8 Flash Next NVFP4 PLE MMap MTP Spark Parameters and Internals

LLM NameQwen3.8 Flash Next NVFP4 PLE MMap MTP Spark
Repository 🤗https://huggingface.co/edougawa/Qwen3.8-Flash-Next-NVFP4-PLE-MMap-MTP-Spark 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size73.2b
Required VRAM3.4 GB
Updated2026-09-06
Maintaineredougawa
Model Typeqwen4_exp
Model Files  1.0 GB: 1-of-248   0.1 GB: 2-of-248   0.0 GB: 3-of-248   0.0 GB: 4-of-248   0.0 GB: 5-of-248   0.1 GB: 6-of-248   0.1 GB: 7-of-248   0.1 GB: 8-of-248   0.0 GB: 9-of-248   0.1 GB: 10-of-248   0.1 GB: 11-of-248   0.1 GB: 12-of-248   0.0 GB: 13-of-248   0.1 GB: 14-of-248   0.0 GB: 15-of-248   0.0 GB: 16-of-248   0.1 GB: 17-of-248   0.1 GB: 18-of-248   0.0 GB: 19-of-248   0.1 GB: 20-of-248   0.1 GB: 21-of-248   0.1 GB: 22-of-248   0.0 GB: 23-of-248   0.1 GB: 24-of-248   0.1 GB: 25-of-248   0.0 GB: 26-of-248   0.1 GB: 27-of-248   0.0 GB: 28-of-248   0.1 GB: 29-of-248   0.1 GB: 30-of-248   0.1 GB: 31-of-248   0.0 GB: 32-of-248   0.1 GB: 33-of-248   0.1 GB: 34-of-248   0.1 GB: 35-of-248   0.0 GB: 36-of-248   0.1 GB: 37-of-248   0.1 GB: 38-of-248
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Transformers Version5.8.0.dev0