// MiniMax · Text LLM
MiniMax-M2: VRAM & local deployment
230B total · 10B active (MoE) parameters. About 156 GB at 4-bit and 509 GB at BF16 with one 8K-token request.
released 2025-10-22licence: Commercial with conditionsmemory figures are estimates
01Specs
| Publisher | MiniMax · MiniMaxAI |
|---|---|
| Family / series | MiniMax · MiniMax-M2 |
| Type | Text LLM (text-generation) |
| Parameters | 230B total · 10B active (MoE) Source: official model card“230 billion total parameters with 10 billion active parameters” |
| Context length | 192K tokens (196,608)max_position_embeddings in config.json |
| Architecture | 62 layers · GQA · MoE |
| Released weights | FP8 (E4M3) · 230 GBdownload |
| Licence | modified-mit · Commercial with conditionsCommercial use allowed under the publisher’s own licence terms (user caps, acceptable-use policy, attribution or region limits). Read it before shipping. |
| Released | 2025-10-22 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Total @ 8K | Total @ 32K | Total @ 128K | Smallest GPU | Mac |
|---|---|---|---|---|---|---|
| BF16 / FP16 (original) | 460 GB | 509 GB | 515 GB | 540 GB | 8 × H100 (640GB) | — |
| FP8 / INT8 / Q8_0 | 244 GB | 271 GB | 278 GB | 303 GB | 4 × RTX PRO 6000 (384GB) | Mac 512GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 139 GB | 156 GB | 162 GB | 187 GB | 4 × RTX PRO 6000 (384GB) | Mac 256GB |
KV cache per request: 8K 2.1 GB · 32K 8.3 GB · 128K 33.3 GB
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- SGLang — mentioned in the official model card
- MLX — mentioned in the official model card
- Transformers — mentioned in the official model card
04Official repositories & quantised builds
1 official repo(s) from MiniMaxAI.
- MiniMax-M2 main
05Other MiniMax models
All 11 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| MiniMax-Music3 | 2.43B | 2.1 GB | 2026-08-07 |
| MiniMax-H3 | 33.1B | 22.6 GB | 2026-07-28 |
| MiniMax-M3 | 428B / 23B | 286 GB | 2026-06-02 |
| MiniMax-M2.7 | 228.7B | 155 GB | 2026-04-09 |
| MiniMax-M2.5 | 228.7B | 155 GB | 2026-02-12 |
| MiniMax-M2.1 | 228.7B | 155 GB | 2025-12-20 |
| MiniMax-M1-80k | 456B / 45.9B | 305 GB | 2025-06-13 |
| MiniMax-M1-40k | 456B / 45.9B | 305 GB | 2025-06-05 |
06Sources
Data checked 2025-12-23. Parameters, context and licence are copied from the official repository; memory figures are our estimates.