Can I run MiniMax Text 01 locally?
MiniMax Text 01 by MiniMaxAI has 456B parameters (48B active per token, 32 experts, 2 used per token). At 4-bit with an 8K context it needs about 263 GB of GPU memory. It fits on 2 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 | 161 GB | 163 GB | 170 GB | 200 GB |
| 3-bit (Q3_K_M) | usable | 210 GB | 211 GB | 218 GB | 248 GB |
| 4-bit (Q4_K_M) | good, most popular | 262 GB | 263 GB | 270 GB | 300 GB |
| 5-bit (Q5_K_M) | very good | 305 GB | 306 GB | 313 GB | 343 GB |
| 6-bit (Q6_K) | near lossless | 350 GB | 352 GB | 359 GB | 389 GB |
| 8-bit (Q8_0) | effectively lossless | 453 GB | 455 GB | 462 GB | 492 GB |
| 16-bit (F16/BF16) | original weights | 852 GB | 853 GB | 860 GB | 890 GB |
Which GPUs and Macs run MiniMax Text 01?
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).
Questions
How much VRAM does MiniMax Text 01 need?
About 263 GB at 4-bit (Q4_K_M) with an 8K context: 260 GB of weights (estimated), 2.5 GB of KV cache and 0.8 GB of runtime overhead. At 8-bit it needs about 455 GB.
What is the smallest GPU that runs MiniMax Text 01?
No single consumer GPU in our table fits it at Q4_K_M with 8K context; the smallest option that does is the Mac M3 Ultra 512GB (512 GB).
Can I run MiniMax Text 01 on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M3 Ultra 512GB or larger, using the default macOS GPU memory limit.
Model facts
| Hugging Face repo | MiniMaxAI/MiniMax-Text-01 |
| Parameters | 456,089,655,296 (456B) · ~48B active (computed from config) |
| Layers / hidden size | 80 / 6144 |
| Attention | GQA; 64 heads, 8 KV heads, head dim 128 |
| KV cache per token (FP16) | 320.0 KiB |
| Max context | 10,240,000 tokens |
| License | — |
| Released on HF | Jan 12, 2025 |
| Downloads (30d) / likes | 3,322 / 656 |
Sources: Hugging Face model API · config.json (MiniMaxAI/MiniMax-Text-01) · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.