Laya alternatives
Jev was released in September 2026, and within weeks several open models with the same typed-question interface appeared. Laya is a 322M to 421M encoder. Most alternatives are open LLMs, mostly Qwen, fine-tuned at 0.5B to 35B parameters to score options without generating text. They trade speed for accuracy.
472 projects
laya-snag-finetune
Adityaakr
Fine-tunes and evaluates Laya as a pull-request requirement verification engine
jev-laya-trader
lucasmartins-ai
A paper-trading system uses Jev and a local Laya model to judge trading signals
poc-laya-model
CtrlShiftCoder
A Spanish-language evaluation toolkit benchmarks Laya and provides local and HTTP backends
ai-agents-and-laya-system-meld
ManasviAtGitHub
Uses Laya for perception and speaker selection in a multi-agent MELD conversation system
playwright-cli-laya-bakeoff
NerdishShah
Evaluates local Laya in a Playwright CLI workflow for adding a product to a Shopify cart
laya_ai_model_demo
lalithdabilpuram01
Tests Laya on labelled support emails and measures inference latency across local devices
testing_arena_jev_vs_laya
Shadowsweep
Compares Jev and Laya in an automated security attack-detection and defense system
elevator-decision-arena
CircleCI-Research
Benchmarks Jev, Laya, and classic algorithms for simulated elevator dispatch decisions
photo-decision-studio
nsdkoo
Compares local Laya and DeepSeek on photo classification using image descriptions
near_agi
yassinebkr
Evaluates and post-trains Laya as a local transition predictor for agent planning
jev-labs
valdepeace
A TypeScript harness compares Jev, Kev and Laya typed-decision engines and publishes experiment results
chess-war
jhonsu01
A pixel-art chess match pits local Laya against Jev using identical typed questions
triage-incident
mumit
A synthetic network-incident benchmark evaluates Laya alongside Jev, Kev and other models
system1bench
CYMCharming
A reproducible benchmark evaluates Laya and other models on typed decisions, safety and robustness
system-one-on-snapdragon
esterhuizen
Setup scripts and benchmarks run open typed-decision models, including Laya, on Snapdragon hardware
local-jev-bench
tak-bro
Benchmarks local Jev-style decision models, including Laya, on Apple Silicon
RayCodes_Mica_4B
47thtechcorner
Compares Mica and Laya decision models in a real-time Pac-Man evasion game
jev-vs-laya-inbox-test
joshpocock
A tool to compare Jev and Laya on inbox classification and fine-tune Laya on labeled email
onesystem-ab
micahn
A comparison of the Laya, Julia and Rizzo decision models across shared test cases
QLaya
saipy10
An experiment distills and quantizes Laya decision models for faster on-device inference
laya-on-lambda
manu-mishra
Experiments with running the Laya decision model on CPU-only AWS Lambda
laya-decision-benchmark
Zerolxgic
Evaluates the Laya decision model under decomposition, distribution shift, and live agent-system inputs
laya-neuro
Aditharavind
Fine-tunes Laya as a calibrated EEG cognitive-workload classifier and evaluates subject-aware performance
laya-windows
astrodevit-creator
Runs the Laya decision model locally on Windows and Linux with PyTorch, CUDA, or CPU
The models
Sizes and licences are from each model's Hugging Face card.
| model | maker | sizes | licence |
|---|---|---|---|
| Kev | Jared Palmer | 0.5B to 27B (benchmarked: 0.8B, 4B, 9B) | Apache 2.0 |
| Decider | Mapika | 0.8B to 35B, plus a 2B vision model | Apache 2.0 |
| Clef, Clef-flash | Cloudflare | 27B, 9B | Apache 2.0 |
| GLiNER2.5-Decide | Fastino | 340M English, 287M multilingual, 1B | Apache 2.0 |
| Julia-1 | Supersonic Labs | 144M | Apache 2.0 |
| Jebadiah | Frontier Infra | 4B, 9B, 27B | Apache 2.0 |
| pplx-decider | Perplexity | ~26B ("27b" in the name) | Apache 2.0 |
- Kev runs a frozen Qwen3.5 base prefill-only, with a LoRA adapter and a pointer head over the options. The card says states of up to 65,536 tokens are served and 8,192 are validated.
- Mapika Decider calls itself an open reproduction of the System One model class. Its training code and data registry are on GitHub.
- Clef and Clef-flash read text, JSON, images and video, per their cards. Cloudflare's announcement says they are Jev-API compatible and also served on Workers AI.
- GLiNER2.5-Decide is a classification-only member of the GLiNER2.5 family: any label set at call time, single- or multi-label.
- Julia-1 is, like Laya, an encoder: it starts from mmBERT-small. See ModernBERT and mmBERT in Laya.
- Jebadiah ships a standalone server that answers
POST /v1/systemoneon one CUDA GPU or an Apple Silicon Mac. - pplx-decider v1.1 uses a separate decision readout instead of a normal language-model head, so its card asks you to use the included inference code.
The hosted reference is Jev from TypeSafe. Its weights are closed and it is billed per input token. The differences from Laya are in Laya vs Jev.
What independent benchmarks found
akitaonrails (October 10, 2026) used synthetic, AI-assisted cases in English and Brazilian Portuguese without independent human labels. Chance was about 31%. Local models ran on a Ryzen AI Max+ 395. Compact-set accuracy and median latency:
| model | accuracy | latency |
|---|---|---|
| Jev (hosted) | 97.6% | 255 ms |
| Clef (hosted) | 95.8% | 302 ms |
| Perplexity Decider 1.1 | 99.4% | 1,547 ms |
| Jebadiah 4B v2 | 90.5% | 205 ms |
| Kev 9B | 88.1% | 561 ms |
| Kev 4B | 87.5% | 246 ms |
| Mapika Decider | 87.5% | 186 ms |
| Clef-flash (local) | 87.5% | 618 ms |
| Kev 0.8B | 63.1% | 86 ms |
| GLiNER2.5-Decide (English only) | 52.4% | 208 ms |
| Laya (English) | 42.9% | 41 ms |
| Julia-1 | 31.5% | 12 ms (GPU) |
The author's conclusion: if Jev-like accuracy is a requirement, Laya, Julia-1 and the 0.6B Decision 3.0 Edge are not usable out of the box. He also notes that judging these small encoders by the accuracy column alone misreads them: they are built to be fine-tuned and run at the edge. Fine-tuning was not tested.
Arize (October 2026) ran a bracket of hallucination detection on RAGTruth, LLM-evaluator suites and agent routing. Balanced accuracy on RAGTruth was 85.5% for Jev, 85.2% for Clef 27B, 76.8% for Kev 9B and 59.8% for laya-multilingual. Laya was the fastest model at 0.04 s p50 on an M4 Max, and had the highest calibration error (0.330).
systemonemodels.ai lists 29 open Jev alternatives with the accuracy each publisher reports. Those figures come from different test sets, so they cannot be compared with each other.
How to choose
- Speed, CPU or on-device: the encoders. Laya and Julia-1 answer in tens of milliseconds, and Laya has the most ports, from Mac to the browser. Plan to fine-tune or to keep a fallback for hard cases.
- Accuracy without training: the 4B and larger models. They need a GPU or an Apple Silicon Mac with enough memory, and they are several times slower.
- No servers: Jev, Clef on Workers AI, or a hosted Laya API.
Whichever you pick, run a few hundred of your own labelled examples through two or three candidates. The rankings above come from small or synthetic sets, and their authors say so.
More ways to use Laya