MiniMax · 428B (23B active) · Mixture of Experts
M3 update for agentic coding, computer use and cybersecurity — DSpark speculative decoding, 1M context Check if your GPU or Mac can run MiniMax M3.1 Flash locally — 239.2 GB min, 398.6 GB recommended.
2026-101024K context
Mixture of Experts
Total experts: 128
Active experts: 4
Active params: 23.0B
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 137.5 GB | low | — |
| Q3_K_M | 3 | 192.3 GB | moderate | — |
| Q4_K_M | 4 | 219.7 GB | good | — |
| Q5_K_M | 5 | 274.5 GB | good | — |
| Q6_K | 6 | 329.4 GB | excellent | — |
| Q8_0 | 8 | 439 GB | excellent | — |
| F16 | 16 | 877.4 GB | lossless | — |
Can I run MiniMax M3.1 Flash locally?
- Can I run MiniMax M3.1 Flash locally?
- MiniMax M3.1 Flash needs about 239.2 GB of memory at a minimum and 398.6 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does MiniMax M3.1 Flash need?
- At Q4_K_M, MiniMax M3.1 Flash uses about 219.7 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.