MiniMax M2.5 Tiny is an open-source language model by morriszjm. Features: 5.2b LLM, VRAM: 6.4GB, Context: 192K, License: other, LLM Explorer Score: 0.28.
Conversational Custom code Endpoints compatible Fp8 Minimax m2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/morriszjm/MiniMax-M2.5-tiny
MiniMax M2.5 Tiny Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
MiniMax M2.5 Tiny Parameters and Internals
| LLM Name | MiniMax M2.5 Tiny |
| Repository 🤗 | https://huggingface.co/morriszjm/MiniMax-M2.5-tiny |
| Model Size | 5.2b |
| Required VRAM | 6.4 GB |
| Updated | 2026-05-17 |
| Maintainer | morriszjm |
| Model Type | minimax_m2 |
| Model Files | |
| Model Architecture | MiniMaxM2ForCausalLM |
| License | other |
| Context Length | 196608 |
| Model Max Length | 196608 |
| Transformers Version | 4.46.1 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 200064 |
Rank the MiniMax M2.5 Tiny Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 53834 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a