MiniMaxAI / text-generation updated 6 months ago

MiniMax-M2.5

Name: MiniMax-M2.5
Author: MiniMaxAI

Join Our 💬 WeChat 🧩 Discord community. MiniMax Agent ⚡️ API MCP MiniMax Website 🤗 Hugging Face 🚀 Hugging Face API 🐙 GitHub 🤖️ ModelScope 📄 License: Modified-MIT

Params

228.7 B

Context

196,608

Downloads 30d

324 K

Likes

1,506

Licence: other Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 56 days

▲ 353 K in the last 30 days (52.1%)

790 K324 K

Jul 28Aug 15Sep 3Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f8_e4m3	230.1 GB	288.0 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 192K ctx	230.1 GB	1,077.0 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/minimax-m2-5
{
  "hf_id": "MiniMaxAI/MiniMax-M2.5",
  "params_b": 228.70,
  "context_length": 196608,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 323999,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 288.0 }
  ],
  "updated_at": "2026-07-28T18:04:09Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: MiniMaxM2ForCausalLM
Parameters: 228.7 B
Tensor type: F8_E4M3
Context length: 196,608
Vocabulary: 200,064
Layers / heads: 62 / 48
Licence: other
First seen on the Hub: 2026-02-12
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative MiniMax-M2.5-NVFP4 nvidia 222 K

Compare with any text-generation model

Popular comparisons

gpt-oss-120b 5.0 M Qwen-72B 4.2 M DeepSeek-V4-Flash-0731 4.1 M DeepSeek-V4-Flash 1.6 M MiniMax-M2.7 1.4 M Qwen2.5-72B-Instruct-AWQ 475 K