inclusionAI/Ling-3.0-flash-Sante
just landedmodel
Text generation model from inclusionAI (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 127B total, 5.1B active (512 experts, 8 per token). Context: 256K tokens (config). License: mit.
- Org
- inclusionAI
- Released
- 2026-10-19
- Status
- just landed
- License
- mit (permissive)
- Parameters
- 127.5B total, 5.1B active
- Architecture
- MoE · 512 experts, 8/token · BailingMoeV3ForCausalLM
- Context
- 262,144 tokens
- Task
- text-generation · text
- Signal
- 54 HF likes · 441 downloads
Runs on
real quant files; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~81.8 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), Strix Halo 128GB unified (~96GB usable), Mac 128GB, CPU only, 128GB RAM (slow)
- Q8 ~137.0 GB: 2× DGX Spark (256GB), Mac 192GB, Mac 256GB, CPU only, 256GB RAM (slow)
- FP16 ~256.5 GB: Mac 512GB
Links
First published here 2026-10-19 · updated 2026-10-22 · markdown · JSON