nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16
main boardmodel
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16 is the base vision-language checkpoint of the Nemotron 3.5 Super family. Mixture-of-experts, 124B total, 12B active (512 experts, 22 per token). Context: 256K tokens (config). License: openmdw-1.1.
- Org
- nvidia
- Released
- 2026-10-12
- Status
- main board
- License
- openmdw-1.1 (permissive)
- Parameters
- 124.5B total, 12.0B active
- Architecture
- MoE · 512 experts, 22/token · NemotronH_Omni_Reasoning_V3
- Context
- 262,144 tokens
- Task
- image-text-to-text · vision
- Signal
- 54 HF likes · 1920 downloads
Runs on
mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~86.3 GB (estimated size): 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), Strix Halo 128GB unified (~96GB usable), Mac 128GB, CPU only, 128GB RAM (slow)
- Q8 ~143.8 GB (estimated size): 2× DGX Spark (256GB), Mac 192GB, Mac 256GB, CPU only, 256GB RAM (slow)
- FP16 ~260.5 GB: Mac 512GB
Links
First published here 2026-10-12 · updated 2026-10-12 · markdown · JSON