facebook/meta-encoder-v1
just landedmodel
Feature extraction model from facebook (HF pipeline tag; the card has no one-line description). Dense, 28B params. Context: 128K tokens (config).
- Org
- Released
- 2026-11-12
- Status
- just landed
- License
- unknown
- Parameters
- 28.4B
- Architecture
- dense · MuseGlimmerModel
- Context
- 131,072 tokens (config.json)
- Task
- feature-extraction · embedding
- Signal
- 39 HF likes · 331 downloads
Runs on
mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~18.5 GB (estimated size): 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~31.6 GB (estimated size): 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~58.4 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 2026-11-12 · updated 2026-11-12 · markdown · JSON