LLM EXPLORER 67,078 MODELS INDEXED

Qwen3.8 Flash Next NanoSeedLM P4 by txgsync

By txgsync · 377 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next NanoSeedLM P4 is an open-source language model by txgsync. Features: 97b LLM, VRAM: 117.1GB, License: other, LLM Explorer Score: 0.31.

  Arxiv:2406.11235   Arxiv:2410.10714   4-bit   Apple-silicon Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   Cuda   Custom code   Image-text-to-text   Lfsr   Metal   Mlx   Mlx-vlm   Moe   Nanoseedlm   Nslm   Omlx   Qwen3.8-flash-next   Qwen4 exp   Region:us   Research-preview   Safetensors   Seedlm   Seeds   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/txgsync/Qwen3.8-Flash-Next-NanoSeedLM-P4 

Qwen3.8 Flash Next NanoSeedLM P4 Parameters and Internals

LLM NameQwen3.8 Flash Next NanoSeedLM P4
Repository 🤗https://huggingface.co/txgsync/Qwen3.8-Flash-Next-NanoSeedLM-P4 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size97b
Required VRAM117.1 GB
Updated2026-11-10
Maintainertxgsync
Model Typeqwen4_exp
Model Files  0.9 GB: 1-of-25   2.5 GB: 8-of-25   4.2 GB: 9-of-25   4.2 GB: 10-of-25   4.2 GB: 11-of-25   4.2 GB: 12-of-25   4.2 GB: 13-of-25   4.2 GB: 14-of-25   4.2 GB: 15-of-25   4.2 GB: 16-of-25   4.2 GB: 17-of-25   4.2 GB: 18-of-25   4.2 GB: 19-of-25   4.2 GB: 20-of-25   4.2 GB: 21-of-25   4.2 GB: 22-of-25   4.2 GB: 23-of-25   4.2 GB: 24-of-25   2.4 GB: 25-of-25   0.9 GB: 1-of-33   1.8 GB: 2-of-33   1.8 GB: 3-of-33   1.8 GB: 4-of-33   1.8 GB: 5-of-33   1.8 GB: 6-of-33   1.8 GB: 7-of-33   1.8 GB: 8-of-33   1.8 GB: 9-of-33   1.8 GB: 10-of-33   1.8 GB: 11-of-33   1.8 GB: 12-of-33   1.8 GB: 13-of-33   1.8 GB: 14-of-33   1.8 GB: 15-of-33   1.8 GB: 16-of-33   1.8 GB: 17-of-33   1.8 GB: 18-of-33   1.8 GB: 19-of-33   1.8 GB: 20-of-33   1.8 GB: 21-of-33   1.8 GB: 22-of-33   1.8 GB: 23-of-33   1.8 GB: 24-of-33   1.8 GB: 25-of-33
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Transformers Version5.8.0.dev0