LLM EXPLORER 65,695 MODELS INDEXED

MiniMax M3.1 Flash EXL3 SAGE 2.15bpw by vcruz305

By vcruz305 · 142 downloads
HF Repo ↗ Copy URL

MiniMax M3.1 Flash EXL3 SAGE 2.15bpw is an open-source language model by vcruz305. Features: 58.4b LLM, VRAM: 117GB, License: other.

  Arxiv:2606.13392 Base model:minimaxai/minimax-m... Base model:quantized:minimaxai...   Conversational   Custom code   En   Exl3   Exllamav3   Image-text-to-text   Minimax m3 vl   Moe   Quantized   Region:us   Safetensors   Sage   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/vcruz305/MiniMax-M3.1-Flash-EXL3-SAGE-2.15bpw 

MiniMax M3.1 Flash EXL3 SAGE 2.15bpw Parameters and Internals

LLM NameMiniMax M3.1 Flash EXL3 SAGE 2.15bpw
Repository 🤗https://huggingface.co/vcruz305/MiniMax-M3.1-Flash-EXL3-SAGE-2.15bpw 
Base Model(s)  MiniMaxAI/MiniMax-M3.1-Flash   MiniMaxAI/MiniMax-M3.1-Flash
Model Size58.4b
Required VRAM117 GB
Updated2026-10-27
Maintainervcruz305
Model Typeminimax_m3_vl
Model Files  7.6 GB: 1-of-16   7.6 GB: 2-of-16   7.6 GB: 3-of-16   7.6 GB: 4-of-16   7.6 GB: 5-of-16   7.6 GB: 6-of-16   7.6 GB: 7-of-16   7.6 GB: 8-of-16   7.6 GB: 9-of-16   7.6 GB: 10-of-16   7.6 GB: 11-of-16   7.6 GB: 12-of-16   7.6 GB: 13-of-16   7.6 GB: 14-of-16   7.6 GB: 15-of-16   3.0 GB: 16-of-16
Supported Languagesen zh
Model ArchitectureMiniMaxM3SparseForConditionalGeneration
Licenseother
Model Max Length40960000
Transformers Version4.52.4
Tokenizer ClassPreTrainedTokenizerFast
Padding Token]!p~[
Torch Data Typebfloat16