Can I run MiMo V2.6 Pro RL locally?
MiMo V2.6 Pro RL by XiaomiMiMo has 1.02T parameters (45B active per token, 384 experts, 8 used per token). At 4-bit with an 8K context it needs about 587 GB of GPU memory. It fits on 1 of 65 GPUs and Macs we track.
GGUF Q8_0 file was 0% of the size expected from the parameter count, so this page uses size estimates instead of real file sizes.
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 | 360 GB | 362 GB | 372 GB | 411 GB |
| 3-bit (Q3_K_M) | usable | 469 GB | 470 GB | 480 GB | 519 GB |
| 4-bit (Q4_K_M) | good, most popular | 585 GB | 587 GB | 597 GB | 636 GB |
| 5-bit (Q5_K_M) | very good | 682 GB | 684 GB | 693 GB | 733 GB |
| 6-bit (Q6_K) | near lossless | 785 GB | 786 GB | 796 GB | 835 GB |
| 8-bit (Q8_0) | effectively lossless | 1016 GB | 1017 GB | 1027 GB | 1067 GB |
| 16-bit (F16/BF16) | original weights | 1910 GB | 1912 GB | 1922 GB | 1961 GB |
Which GPUs and Macs run MiMo V2.6 Pro RL?
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?
Xiaomi: MiMo-V2.6-Pro is on OpenRouter at $0.435 per 1M input tokens and $0.87 per 1M output tokens. Price details and history →
Questions
How much VRAM does MiMo V2.6 Pro RL need?
About 587 GB at 4-bit (Q4_K_M) with an 8K context: 583 GB of weights (estimated), 3.3 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 1017 GB.
What is the smallest GPU that runs MiMo V2.6 Pro RL?
No single consumer GPU in our table fits it at Q4_K_M with 8K context.
Can I run MiMo V2.6 Pro RL on a Mac?
Not at Q4_K_M with 8K context on any Mac in our table, even a 512 GB Mac Studio, using the default GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
MiMo V2.5 Pro
1.02T · 590 GB at 4-bitMiMo V2.6 Flash RL
311B · 179 GB at 4-bitMiMo V2.5
311B · 180 GB at 4-bitKimi K2 Instruct
1.03T · 579 GB at 4-bitKimi K2 Base
1.03T · 586 GB at 4-bitKimi K2 Thinking
1.03T · 580 GB at 4-bitModel facts
| Hugging Face repo | XiaomiMiMo/MiMo-V2.6-Pro-RL |
| Parameters | 1,024,216,603,392 (1.02T) · ~45B active (computed from config) |
| Layers / hidden size | 70 / 6144 |
| Attention | GQA; 128 heads, 8 KV heads, head dim 192 |
| KV cache per token (FP16) | 420.0 KiB |
| Max context | 1,048,576 tokens |
| License | mit |
| Released on HF | Sep 21, 2026 |
| Downloads (30d) / likes | 23,738 / 822 |
Sources: Hugging Face model API · config.json (XiaomiMiMo/MiMo-V2.6-Pro-RL) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.