VillanovaAI/Villanova2-15B-A3B-Base

archived · low-signalmodel

Prompting a base model means continuing it, not asking. Mixture-of-experts, 15B total, 3B active. License: apache-2.0.

Org: VillanovaAI
Released: 2026-10-26
Status: archived · low-signal
License: apache-2.0 (permissive)
Parameters: 15.5B total, 3.0B active
Architecture: MoE
Task: text-generation · text
Signal: 4 HF likes · 17 downloads
Weights: gated
Archived: 2026-11-13 (no longer listed by the collector; stats as last seen)

Runs on

mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.

Q4 ~11.6 GB (estimated size): 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), 16GB GPU (7800 XT / 9070 XT), Mac 16GB, Mac 24GB
Q8 ~18.8 GB (estimated size): 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Arc B60 24GB, Arc B70 32GB, Mac 36GB, CPU only, 32GB RAM (slow)
FP16 ~33.3 GB: 48GB GPU (RTX 6000 Ada / A6000), 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 48GB, Mac 64GB (M1 Max), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 64GB RAM (slow), CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)