inception42/Jais-3-375B-A23B
just landed · new, unvettedmodel
New, unvetted: created or first seen in the last few days, not from a trusted org and not past the signal threshold yet.
Jais-3-375B-A23B is the flagship of the Jais-3 family: a sparse Mixture-of-Experts model that stores 375B parameters and runs 23B per token, with a 512K context window. Mixture-of-experts, 379B total, 23B active (192 experts, 8 per token). Context: 512K tokens (config). License: apache-2.0.
- Org
- inception42
- Released
- 2026-09-29
- Status
- just landed · new, unvetted
- License
- apache-2.0 (permissive)
- Parameters
- 379.2B total, 23.0B active
- Architecture
- MoE · 192 experts, 8/token · K2HorizonForCausalLM
- Context
- 524,288 tokens
- Task
- text-generation · text
- Signal
- 5 HF likes · 977 downloads
Runs on
mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~230.5 GB (estimated size): Mac 512GB, CPU only, 256GB RAM (slow)
- Q8 ~405.9 GB (estimated size): no listed device
- FP16 ~761.3 GB: no listed device
Links
First published here 2026-09-29 · updated 2026-10-25 · markdown · JSON