Kev 27B measured on 3 of 12 Decision models benchmarks3
BenchmarkByScoreRank
No benchmark matches
—per task?
self-host onlyprice
—output speed?
66Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
bBettermammoth-1 (27B)Open+16%—$0 / —Context: 66K → 16K+1
BetterDecider v1.2Open+14%—$0.02 / —ABetterAutoTrust-JEV-27B v1.1Open+14%——Memory (4-bit): 15 GB → 16 GBSBetterStartLux-Decision v1.1 27BOpen+14%——Memory (4-bit): 15 GB → 16 GBvBetterD3 TurboOpen+13%——Context: 66K → 33KModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)Open+16%—$0 / —Context: 66K → 16K+1Decider v1.2Open+14%—$0.02 / —AAutoTrust-JEV-27B v1.1Open+14%——Memory (4-bit): 15 GB → 16 GBSStartLux-Decision v1.1 27BOpen+14%——Memory (4-bit): 15 GB → 16 GBvD3 TurboOpen+13%——Context: 66K → 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 modelsJevBench v1.6.15.8#4
JevBench v1.6.37 · open capability78.9#1
FAQ
How much does Kev 27B cost?›
There is no per-unit API price: self-host only.
Is Kev 27B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Kev 27B, and what is it best at?›
#20 of 99 in Decision models.
Is Kev 27B better than linne-fern 1.0 (27B)?›
On Community Decision Index 0.4.1, Kev 27B scores 59.6 vs 59.7 — about the same.
What is the context window of Kev 27B?›
66K tokens.
When was Kev 27B released? Is there a newer version?›
Released 2026-09-30. It is the current version in its line.
Is Kev 27B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Kev 27B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Kev 27B read images?›
No, it accepts text only.
What is Kev 27B?›
Kev 27B is an open-weights language model from Jared Palmer, released Sep 2026.
What are the best alternatives to Kev 27B?›
mammoth-1 (27B) (better).