sthanika-ai/Sieve-31B-v3
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.
Sieve-31B-v3 is a decision model from the Sieve family. Dense, 31B params. Context: 256K tokens (config). License: apache-2.0.
- Org
- sthanika-ai
- Released
- 2026-10-27
- Status
- just landed · new, unvetted
- License
- apache-2.0 (permissive)
- Parameters
- 31.3B
- Architecture
- dense · Gemma4ForConditionalGeneration
- Context
- 262,144 tokens
- Task
- text-classification · text
- Signal
- 6 HF likes · 287 downloads
Runs on
real quant files; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~27.8 GB: 32GB GPU (5090), Mac 48GB
- Q8 ~41.7 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~71.6 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 2026-10-27 · updated 2026-10-31 · markdown · JSON