internlm/Sage-S2.1-Flash
just landedmodel
Sage S2.1 Flash is a scientific multimodal model from Shanghai Artificial Intelligence Laboratory designed for research tasks that require multiple rounds of analysis and verification. Mixture-of-experts, 321B total (288 experts, 8 per token). Context: 1M tokens (config).
- Org
- internlm
- Released
- 2026-11-15
- Status
- just landed
- License
- unknown
- Parameters
- 321.3B
- Architecture
- MoE · 288 experts, 8/token · Glm5NextForConditionalGeneration
- Context
- 1,048,576 tokens (config.json)
- Signal
- 17 HF likes · 22 downloads
Runs on
mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~194.2 GB (estimated size): 2× DGX Spark (256GB), CPU only, 256GB RAM (slow)
- Q8 ~342.8 GB (estimated size): Mac 512GB
- FP16 ~644.2 GB: no listed device
Links
First published here 2026-11-15 · updated 2026-11-16 · markdown · JSON