Local AI Advisor

MiMo-V2.6-Pro-RL on local hardware

Estimated comfort for repository coding with Aider on a MacBook Pro M4 Pro 48GB.

MiMo-V2.6-Pro-RLOpen source

XiaomiMiMo · mit · 103,098 downloads

Hugging Face
Mixture of expertsVisionReasoning / thinking mode
Parameters
1.0T exact
Active per token
≈41B (8 of 384 experts)
Context window
1M tokens
Attention
Sliding-window + global layers
Layers · KV heads · head dim
70 · 8 · 192
KV cache
0 KB/token · 0.1 GB at 32K
Tool calling
good (from chat template)
Thinking
good (from chat template)
Vision
good (from config)
Commercial use
allowedRetain the required license and attribution notices
Import confidence
medium · capabilities estimated

Weights by quantization

MXFP4

516 GB

gguf file size

Q4_K_M

575 GB

gguf file size

  • • vision: good, inferred from config (low confidence).
  • • Capability ratings are estimated from model size and name — this model hasn't been assessed by hand.
  • • GGUF sizes come from community conversions matched by model name; equivalence and runtime support are not verified. MLX conversion availability is unverified.

MiMo-V2.6-Pro-RL — MXFP4

Does not fit in memory

Does Not Fit

Needs ≈514 GB but only ≈37 GB is available after the OS, other apps and Aider.

High confidence
Check with your hardware and workload