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.
468 projects
laya-cpu-benchmark
taiheqi718-art
Measures steady-state CPU latency for the multilingual Laya model
decision-models-under-pressure
gazelle93
A benchmark compares seven decision models as candidate lists grow, options reorder and distractors become harder
laya-mlx-zh
ZLHAOOO
Provides Chinese fine-tuned Laya weights, training data, and evaluations for Apple Silicon MLX
pacman-arena
hakan-gecili
Compares Laya with other local decision models playing Pac-Man under identical conditions
laya-typed-decisions-421m-coreml-ane
NMTZ
Provides fixed-shape Core ML artifacts converted from the 421M Laya typed-decisions checkpoint
laya-typed-decisions
akshatbindal
Fine-tunes Laya on the typed-decisions benchmark and compares results with Jev
laya-mini-cpu-research
VynoDePal
Shares experimental CPU student-model checkpoints and controlled evaluations using Laya as the teacher
laya-ko
2nugu
Fine-tunes Laya for Korean and evaluates it on classification, relation extraction, inference, and similarity tasks
laya-typed-decisions
Ankit1106
Fine-tunes Laya on typed-decision examples and reports held-out evaluation metrics
laya-typed-decisions-turkish-mmlu-10k
canbingol
A Laya checkpoint fine-tuned on 10,000 Turkish MMLU typed-decision examples
laya-browser-agent
knpatil
Fine-tunes a ModernBERT-based Laya model for autonomous browser control
laya-typed-decisions
yashchouhann
Fine-tunes Laya on a typed-decisions benchmark and reports comparative results
laya-fullft-typed-decisions
jjshin
Fine-tunes Laya with pure PyTorch RLCD for typed decisions and jailbreak detection
decision-model-playground
tedliou
A local web playground comparing Laya and Jev for recommending articles
jev-vs-open-decision-models
elcronos
Benchmarks Jev against Laya and PrismNLI on zero-shot text classification tasks
JevCoreML
GodModeAI2025
Provides Core ML decision models, a Swift package, an HTTP server, and a demo app
laya
xosi
Runs Laya typed-decision inference locally on Apple Silicon with MLX
laya-jev-arena
dante01yoon
Compares local Laya and hosted Jev models in games and measurement tools
chinese-workflow-decision-bench
Adkid-Zephyr
Benchmarks Jev and Laya on synthetic Feishu message classification scenarios
stuntdouble
ReallyArtificial
Proxies Jev requests to local decision models and compares their answers on recorded traffic
laya-micro
osamabinIaggin
Prunes and quantizes Laya for low-memory single-board computer deployment
laya-invaders
inhabitants
Uses Laya to choose targets in a Space Invaders game and compares it with a rule baseline
jev-laya-benchmark
EnesDemir143
Benchmarks TypeSafe Jev and Laya-MLX on structured issue classification
laya-learning-demo
Daryl9441
A runnable tutorial teaches Laya decision primitives, routing, fine-tuning, and comparison with Jev
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