Runs on Data centre · Hugging Face ↗
Coding index 60.8 (Artificial Analysis)
Moonshot's ~1-trillion-parameter MoE, tuned specifically for coding — and unlike Kimi K3 the weights ARE openly released. One of the strongest open coders.
Real GGUF file sizes = weight VRAM.
| Quantization | Size |
|---|---|
| Q2_K | 339.5 GB |
| Q3_K_M | 463.6 GB |
| IQ4_XS | 495.1 GB |
| Q4 | 583.7 GB |
| Q8 | 594.5 GB |
~495 GB at Q4 — cluster-scale, tensor / pipeline parallel across many GPUs. Open but not local for most; the hosted per-token price is the realistic route.