facebook/meta-encoder
main boardmodel
Feature extraction model from facebook (HF pipeline tag; the card has no one-line description). 30B params. License: apache-2.0.
- Org
- Released
- 2026-09-30
- Status
- main board
- License
- apache-2.0 (permissive)
- Parameters
- 29.8B
- Task
- feature-extraction · embedding
- Signal
- 28 HF likes · 140 downloads
- Weights
- gated
Runs on
mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~23.2 GB: 32GB GPU (5090), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~35.1 GB (estimated size): 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~63.1 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)
Links
First published here 2026-09-30 · updated 2026-09-30 · markdown · JSON