LLM EXPLORER 65,695 MODELS INDEXED

MiniMax M3.1 Flash NVFP4 GGUF by AMAImedia

By AMAImedia · 1184 downloads
HF Repo ↗ Copy URL

MiniMax M3.1 Flash NVFP4 GGUF is an open-source language model by AMAImedia. Features: 220.5b LLM, VRAM: 200.6GB, License: other, Quantized.

  Arxiv:2606.13392   8-bit   Af   Agent   Am   Ar   As   Ast   Az Base model:lyjonathan/minimax-... Base model:quantized:lyjonatha...   Be   Bg   Bn   Bs   Ca   Ceb   Ckb   Coding   Conversational   Cs   Custom code   Cy   Da   De   El   En   Endpoints compatible   Es   Et   Eu   Fa   Ff   Fi   Fil   Fr   Ga   Gguf   Gl   Gn   Gu   Ha   He   Hi   Hr   Hu   Hy   Id   Ig   Image-text-to-text   Is   It   Ja   Jv   Ka   Kam   Kea   Kk   Km   Kmr   Kn   Ko   Ky   Lb   Lg   Ln   Lo   Lt   Luo   Lv   Mi   Minimax m3 vl   Mk   Ml   Mn   Moe   Mr   Ms   Mt   Multimodal   Mvy   Mxfp8   My   Ne   Nl   No   Nso   Ny   Oc   Om   Or   Pa   Pl   Ps   Pt   Q2   Quantized   Qxp   Region:us   Ro   Ru   Rw   Safetensors   Sd   Sharded   Sk   Skr   Sl   Sn   So   Sr   Sv   Sw   Ta   Te   Tensorflow   Tg   Th   Ti   Tk   Tr   Ug   Uk   Umb   Ur   Uz   Vi   Video   Wo   Xh   Yo   Yue   Zh   Zu
Model Card on HF 🤗: https://huggingface.co/AMAImedia/MiniMax-M3.1-Flash-NVFP4-GGUF 

MiniMax M3.1 Flash NVFP4 GGUF Parameters and Internals

LLM NameMiniMax M3.1 Flash NVFP4 GGUF
Repository 🤗https://huggingface.co/AMAImedia/MiniMax-M3.1-Flash-NVFP4-GGUF 
Base Model(s)  MiniMaxAI/MiniMax-M3.1-Flash   LyJonathan/MiniMax-M3.1-Flash-GGUF   webmp3/Sakura-MiniMax-M3.1-Flash-Q2_K-GGUF   MiniMaxAI/MiniMax-M3.1-Flash   LyJonathan/MiniMax-M3.1-Flash-GGUF   webmp3/Sakura-MiniMax-M3.1-Flash-Q2_K-GGUF
Model Size220.5b
Required VRAM200.6 GB
Updated2026-10-27
MaintainerAMAImedia
Model Typeminimax_m3_vl
Model Files  10.2 GB: 1-of-48   4.2 GB: 2-of-48   4.2 GB: 3-of-48   8.5 GB: 4-of-48   8.5 GB: 5-of-48   8.5 GB: 6-of-48   8.5 GB: 7-of-48   8.5 GB: 8-of-48   8.5 GB: 9-of-48   8.5 GB: 10-of-48   8.5 GB: 11-of-48   8.5 GB: 12-of-48   4.7 GB: 13-of-48   4.2 GB: 14-of-48   4.2 GB: 15-of-48   4.2 GB: 16-of-48   4.2 GB: 17-of-48   4.2 GB: 18-of-48   4.2 GB: 19-of-48   4.2 GB: 20-of-48   4.2 GB: 21-of-48   4.2 GB: 22-of-48   4.2 GB: 23-of-48   4.2 GB: 24-of-48   4.2 GB: 25-of-48   4.2 GB: 26-of-48   4.2 GB: 27-of-48   4.2 GB: 28-of-48   4.2 GB: 29-of-48   4.2 GB: 30-of-48   4.2 GB: 31-of-48   4.2 GB: 32-of-48   4.2 GB: 33-of-48   4.2 GB: 34-of-48   4.2 GB: 35-of-48   4.2 GB: 36-of-48   4.2 GB: 37-of-48
Supported Languagesen ru zh vi kk ja af am ar as az be bg bn bs ca cs cy da de el es et eu fa ff fi fr ga gl gn gu ha he hi hr hu hy id ig is it jv ka km kn ko ky lb lg ln lo lt lv mi mk ml mn mr ms mt my ne nl no ny oc om or pa pl ps pt ro rw sd sk sl sn so sr sv sw ta te tg th ti tk tr ug uk ur uz wo xh yo zu
GGUF QuantizationYes
Quantization Typegguf|q2
Model ArchitectureMiniMaxM3SparseForConditionalGeneration
Licenseother
Transformers Version4.52.4
Torch Data Typebfloat16

Best Alternatives to MiniMax M3.1 Flash NVFP4 GGUF

Best Alternatives
Context / RAM
Downloads
Likes
MiniMax M3.1 Flash0K / 196.4 GB8782381
MiniMax M3.1 Flash0K / 196.4 GB3318
MiniMax M3.1 Flash0K / 196.4 GB321
MiniMax M3 MXFP4 CT AutoRound0K / 200.5 GB471
MiniMax 3.1 Flash DeRisked0K / 183.8 GB341
MiniMax M3.1 Flash0K / 196.4 GB221
Note: green Score (e.g. "73.2") means that the model is better than AMAImedia/MiniMax-M3.1-Flash-NVFP4-GGUF.