decido-ai/decido-1-think-26b-a4b
archived · low-signalmodel
Image text to text model from decido-ai (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 26B total (128 experts, 8 per token). Context: 256K tokens (config). License: apache-2.0.
- Org
- decido-ai
- Released
- 2026-11-06
- Status
- archived · low-signal
- License
- apache-2.0 (permissive)
- Parameters
- 25.8B
- Architecture
- MoE · 128 experts, 8/token · Gemma4ForConditionalGeneration
- Context
- 262,144 tokens (config.json)
- Task
- image-text-to-text · vision
- Signal
- 2 HF likes · 360 downloads
- Archived
- 2026-11-11 (no longer listed by the collector; stats as last seen)
Runs on
mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~18.5 GB (estimated size): 24GB GPU (3090 / 4090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~30.4 GB (estimated size): 32GB GPU (5090), 48GB GPU (RTX 6000 Ada / A6000), Arc B70 32GB, Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~56.6 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 2026-11-06 · updated 2026-11-11 · markdown · JSON