XiaomiMiMo/MiMo-V2.6-Flash-MOPD
main boardmodel
Text generation model from XiaomiMiMo (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 311B total, 15B active (256 experts, 8 per token). Context: 1M tokens (config). License: mit.
- Org
- XiaomiMiMo
- Released
- 2026-09-27
- Status
- main board
- License
- mit (permissive)
- Parameters
- 310.8B total, 15.0B active
- Architecture
- MoE · 256 experts, 8/token · MiMoV2ForCausalLM
- Context
- 1,048,576 tokens
- Task
- text-generation · text
- Signal
- 68 HF likes · 12589 downloads · 3 X likes · 2 X post(s)
Runs on
estimate from params; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~188.7 GB (estimated size): 2× DGX Spark (256GB), Mac 256GB, CPU only, 256GB RAM (slow)
- Q8 ~332.4 GB (estimated size): Mac 512GB
- FP16 ~623.7 GB (estimated size): no listed device
Links
First published here 2026-09-27 · updated 2026-09-27 · markdown · JSON