Can I run MiMo V2.6 Flash RL locally?
MiMo V2.6 Flash RL by XiaomiMiMo has 311B parameters (6.2B active per token, 256 experts, 8 used per token). At 4-bit with an 8K context it needs about 179 GB of GPU memory. It fits on 4 of 65 GPUs and Macs we track.
GGUF Q8_0 file was 1% 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 | 110 GB | 110 GB | 114 GB | 127 GB |
| 3-bit (Q3_K_M) | usable | 143 GB | 143 GB | 147 GB | 160 GB |
| 4-bit (Q4_K_M) | good, most popular | 178 GB | 179 GB | 182 GB | 196 GB |
| 5-bit (Q5_K_M) | very good | 207 GB | 208 GB | 211 GB | 225 GB |
| 6-bit (Q6_K) | near lossless | 239 GB | 239 GB | 243 GB | 256 GB |
| 8-bit (Q8_0) | effectively lossless | 309 GB | 309 GB | 313 GB | 326 GB |
| 16-bit (F16/BF16) | original weights | 580 GB | 581 GB | 584 GB | 598 GB |
Which GPUs and Macs run MiMo V2.6 Flash 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-Flash is on OpenRouter at $0.14 per 1M input tokens and $0.28 per 1M output tokens. Price details and history →
Questions
How much VRAM does MiMo V2.6 Flash RL need?
About 179 GB at 4-bit (Q4_K_M) with an 8K context: 177 GB of weights (estimated), 1.1 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 309 GB.
What is the smallest GPU that runs MiMo V2.6 Flash RL?
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 MiMo V2.6 Flash RL 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 | XiaomiMiMo/MiMo-V2.6-Flash-RL |
| Parameters | 310,756,322,688 (311B) · ~6.2B active (computed from config), low confidence, speed not shown |
| Layers / hidden size | 48 / 4096 |
| Attention | GQA; 64 heads, 4 KV heads, head dim 192 |
| KV cache per token (FP16) | 144.0 KiB |
| Max context | 1,048,576 tokens |
| License | mit |
| Released on HF | Sep 21, 2026 |
| Downloads (30d) / likes | 40,828 / 598 |
Sources: Hugging Face model API · config.json (XiaomiMiMo/MiMo-V2.6-Flash-RL) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.