microsoft/AesCode-32B
main boardmodel
Image text to text model from microsoft (HF pipeline tag; the card has no one-line description). Dense, 33B params. Context: 256K tokens (config). License: apache-2.0.
- Org
- microsoft
- Released
- 2026-09-29
- Status
- main board
- License
- apache-2.0 (permissive)
- Parameters
- 33.4B
- Architecture
- dense · Qwen3VLForConditionalGeneration
- Context
- 262,144 tokens
- Task
- image-text-to-text · vision
- Signal
- 55 HF likes · 1448 downloads
Runs on
real quant files; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~23.6 GB: 32GB GPU (5090), Mac 36GB, Mac 48GB, CPU only, 32GB RAM (slow)
- Q8 ~37.9 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~68.6 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 2026-09-29 · updated 2026-09-29 · markdown · JSON