MiMo-V2-Flash

This model declares a 128-token sliding window, but we could not establish which layers use it. Its architecture publishes the layout as a per-layer array inside the model file rather than as a period in config.json, and we have not yet ingested that array.

A flat context × layers × heads figure would be substantially too high, so we are not showing one. This is tracked as a known gap rather than filled with a guess.

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 162.29 GiB. The real file is 173.97 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

How much VRAM does MiMo-V2-Flash need?

Q4_K_M is exactly 186,798,293,696 bytes (173.97 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.

Is MiMo-V2-Flash a mixture-of-experts model?

Yes — 256 experts, 8 routed per token. Every expert must be resident, but only the routed ones are read per token, which is why its memory requirement and its speed behave very differently.

Which quantization of MiMo-V2-Flash should I use?

Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.