—per task?
price not verifiedprice
—output speed?
16Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
bBettermammoth-1 (27B)Open+100%—$0 / —ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)Open+100%—$0 / —ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)Open+100%—$0 / —ModelScoreCostPer taskWhat changes
SSieve 27B v2Open+74%——SSieve 0.8BOpen-40%——All Sthānika AI models →Run it yourself
Fits onhardware needs not verified yet
LicenceApache-2.0free for commercial use
Benchmarks
in Decision modelsFAQ
How much does Sieve 2B v3 cost?›
There is no per-unit API price: price not verified.
How good is Sieve 2B v3, and what is it best at?›
#62 of 99 in Decision models.
Is Sieve 2B v3 better than Standard One 3B SH (v2)?›
On Community Decision Index 0.4.1, Sieve 2B v3 scores 34.5 vs 35.3 — about the same.
What is the context window of Sieve 2B v3?›
16K tokens.
When was Sieve 2B v3 released? Is there a newer version?›
Released 2026-10-15. It is the current version in its line.
Is Sieve 2B v3 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Sieve 2B v3 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Sieve 2B v3 read images?›
No, it accepts text only.
What is Sieve 2B v3?›
Sieve 2B v3 is an open-weights language model from Sthānika AI, released Oct 2026.
What are the best alternatives to Sieve 2B v3?›
mammoth-1 (27B) (better).