Will this model run on your hardware?
Can I run Xiaomi: MiMo-V2.5 locally?
- 311B parameters (25B active, MoE)
- context up to 1024K
- licence: mit
- #31 in the AIContenders model ranking
- Weights: XiaomiMiMo/MiMo-V2.5 · GGUF: unsloth/MiMo-V2.5-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 329.3 GB |
| UD-Q6_K | 257.0 GB |
| UD-Q5_K_M | 230.2 GB |
| UD-Q4_K_M | 190.9 GB |
| MXFP4 | 185.4 GB |
| UD-Q3_K_M | 140.0 GB |
Run it locally
ollama run hf.co/unsloth/MiMo-V2.5-GGUF:UD-Q4_K_M
llama serve -hf unsloth/MiMo-V2.5-GGUF:UD-Q4_K_M
LM Studio: open unsloth/MiMo-V2.5-GGUF