Can I run MiniMax M3.1 Flash locally?
MiniMax M3.1 Flash by MiniMaxAI has 220B parameters (4.4B active per token, 128 experts, 4 used per token). At 4-bit with an 8K context it needs about 127 GB of GPU memory. It fits on 9 of 65 GPUs and Macs we track.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx | 32K ctx | 128K ctx |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | rough | 78.3 GB | 78.7 GB | 81.5 GB | 92.8 GB |
| 3-bit (Q3_K_M) | usable | 102 GB | 102 GB | 105 GB | 116 GB |
| 4-bit (Q4_K_M) | good, most popular | 127 GB | 127 GB | 130 GB | 141 GB |
| 5-bit (Q5_K_M) | very good | 148 GB | 148 GB | 151 GB | 162 GB |
| 6-bit (Q6_K) | near lossless | 170 GB | 170 GB | 173 GB | 184 GB |
| 8-bit (Q8_0) | effectively lossless | 219 GB | 220 GB | 223 GB | 234 GB |
| 16-bit (F16/BF16) | original weights | 412 GB | 412 GB | 415 GB | 426 GB |
Which GPUs and Macs run MiniMax M3.1 Flash?
Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).
Prefer an API?
MiniMax: MiniMax M3.1 Flash is on OpenRouter at $0.15 per 1M input tokens and $0.60 per 1M output tokens. Price details and history →
Questions
How much VRAM does MiniMax M3.1 Flash need?
About 127 GB at 4-bit (Q4_K_M) with an 8K context: 126 GB of weights (estimated), 0.9 GB of KV cache and 0.8 GB of runtime overhead. At 8-bit it needs about 220 GB.
What is the smallest GPU that runs MiniMax M3.1 Flash?
No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the Mac M2 Ultra 192GB (192 GB).
Can I run MiniMax M3.1 Flash on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M2 Ultra 192GB or larger, using the default macOS GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
MiniMax M2.5
229B · 132 GB at 4-bitMiniMax M2.7
229B · 133 GB at 4-bitMiniMax M2
229B · 132 GB at 4-bitDeepSeek V2 Chat
236B · 135 GB at 4-bitStep 3.7 Flash
201B · 119 GB at 4-bitIntern S1
241B · 139 GB at 4-bitModel facts
| Hugging Face repo | MiniMaxAI/MiniMax-M3.1-Flash |
| Parameters | 220,490,854,016 (220B) · ~4.4B active (computed from config), low confidence, speed not shown |
| Layers / hidden size | 60 / 6144 |
| Attention | GQA; 64 heads, 4 KV heads, head dim 128 |
| KV cache per token (FP16) | 120.0 KiB |
| Max context | 1,048,576 tokens |
| License | other |
| Released on HF | Oct 17, 2026 |
| Downloads (30d) / likes | 65,608 / 597 |
Sources: Hugging Face model API · config.json (MiniMaxAI/MiniMax-M3.1-Flash) · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.