—per task?
price not verifiedprice
—output speed?
262Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
bBettermammoth-1 (27B)unstatedOpen+17%—$0 / —Context: 262K → 16K+2
BetterDecider v1.2Open+16%—$0.02 / —ABetterAutoTrust-JEV-27B v1.1Open+15%——Memory (4-bit): 15 GB → 16 GB+1SBetterStartLux-Decision v1.1 27BOpen+15%——Memory (4-bit): 15 GB → 16 GBvBetterD3 TurboOpen+14%——Context: 262K → 33KModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)unstatedOpen+17%—$0 / —Context: 262K → 16K+2Decider v1.2Open+16%—$0.02 / —AAutoTrust-JEV-27B v1.1Open+15%——Memory (4-bit): 15 GB → 16 GB+1SStartLux-Decision v1.1 27BOpen+15%——Memory (4-bit): 15 GB → 16 GBvD3 TurboOpen+14%——Context: 262K → 33KRun it yourself
estimateFits on✗ 8 GB (phone, laptop)✓ 16 GB · compressed✓ 24 GB GPU · compressed✓ 48 GB GPU · 8-bit✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
Benchmarks
in Decision modelsFAQ
How much does Shisa DE-2.1 (repeat) cost?›
There is no per-unit API price: price not verified.
How good is Shisa DE-2.1 (repeat), and what is it best at?›
#23 of 99 in Decision models.
Is Shisa DE-2.1 (repeat) better than Jev 1.13?›
On Community Decision Index 0.4.1, Shisa DE-2.1 (repeat) scores 58.8 vs 59.2 — about the same.
What is the context window of Shisa DE-2.1 (repeat)?›
262K tokens.
When was Shisa DE-2.1 (repeat) released? Is there a newer version?›
Released 2026-10-19. It is the current version in its line.
Is Shisa DE-2.1 (repeat) open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Shisa DE-2.1 (repeat) locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Shisa DE-2.1 (repeat) read images?›
It accepts text and images, audio, video as input.
What is Shisa DE-2.1 (repeat)?›
Shisa DE-2.1 (repeat) is an open-weights language model from Shisa.AI, released Oct 2026.
What are the best alternatives to Shisa DE-2.1 (repeat)?›
mammoth-1 (27B) (better).