bottlecapai/ThinkingCap-Qwen3.8-27B
archivedmodel
Image text to text model from bottlecapai (HF pipeline tag; the card has no one-line description). 28B params. License: polyform-small-business-1.0.0.
- Org
- bottlecapai
- Released
- 2026-09-23
- Status
- archived
- License
- polyform-small-business-1.0.0 (restricted)
- Parameters
- 27.8B
- Task
- image-text-to-text · vision
- Signal
- 178 HF likes · 4404 downloads
- Weights
- gated
- Archived
- 2026-10-23 (aged out (older than 30 days); stats as last seen)
Runs on
real quant files; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~20.8 GB: 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~32.4 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~58.1 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 2026-09-23 · updated 2026-10-23 · markdown · JSON