mingqiancha233/Socrates-Image-1.0-31B
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.
Socrates-Image-1.0 is a self-contained dense text-to-image model with recurrent visual-semantic feedback. 31B params. License: qwen-research.
- Org
- mingqiancha233
- Released
- 2026-10-22
- Status
- just landed · new, unvetted
- License
- qwen-research (restricted)
- Parameters
- 31.0B
- Architecture
- SocratesImageModel
- Task
- text-to-image · image
- Signal
- 2 HF likes · 25 downloads
Runs on
estimate from params; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~22.2 GB (estimated size): 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, Mac 48GB, CPU only, 32GB RAM (slow)
- Q8 ~36.5 GB (estimated size): 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~65.6 GB (estimated size): 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 2026-10-22 · updated 2026-10-23 · markdown · JSON