MiMo-V2.6-Flash-RL on local hardware
Estimated comfort for repository coding with Aider on a MacBook Pro M4 Pro 48GB.
MiMo-V2.6-Flash-RLOpen source
XiaomiMiMo · mit · 105,330 downloads
Mixture of expertsVisionReasoning / thinking mode
- Parameters
- 311B exact
- Active per token
- ≈12B (8 of 256 experts)
- Context window
- 1M tokens
- Attention
- Sliding-window + global layers
- Layers · KV heads · head dim
- 48 · 4 · 192
- KV cache
- 0 KB/token · 0.0 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
156 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-Flash-RL — MXFP4
Does not fit in memory
Needs ≈156 GB but only ≈37 GB is available after the OS, other apps and Aider.
High confidence