Kev
A family of lightweight decision models built on Qwen open-source models, focused on structured judgment tasks such as routing decisions, intent classification, and content filtering. The models are positioned as low-cost, fast-response, small-scale specialized models.
Timeline (last 90 days)
Commit #18976 enables MLX to load the Kev model, and to simultaneously load its FP32 decision head and release metadata.
Commit #18976 supports System One scoring on top of the shared state cache, and adds Kev-specific resource limits.
Ollama released the v0.40.4-rc1 pre-release, with the core change being the introduction of Kev decision scoring capability in the MLX backend.
Open-source projects attempting to replicate Jev's capabilities include nano Jeff, a project formerly known as open Jeff, and a family of micro decision models named Kev.
Laya, Kev, and Ollaya are three open-source alternatives frequently mentioned in the context of Jev.
For the policy-intensive customer service routing pilot task, Kev is a stronger starting point, while Laya is faster and has lower memory usage but requires improvement under these rules before it can be trusted.
In cases requiring contextual understanding, Kev correctly handled the situation where a customer explicitly stated they did not want a refund and only needed a password reset by selecting technical support, while Laya incorrectly selected billing due to the presence of billing-related vocabulary.
Kev is an open-source classification model based on Qwen 3.5's 0.8B base model, with LoRA fine-tuning weights merged in, using unidirectional reading and making decisions through a pointer head.
Tested on the same machine equipped with a Spark CPU and limited to three threads, Laya's median call latency was 541 milliseconds and Kev's was 756 milliseconds, with the 95th percentile at approximately 607 and 802 milliseconds respectively.
Under the original option order in the customer service ticket routing test, Kev scored 26/30 and Laya scored 12/30.
3 more timeline events
All Facts (13)
Commit #18976 enables MLX to load the Kev model, and to simultaneously load its FP32 decision head and release metadata.
50%UnverifiedCommit #18976 supports System One scoring on top of the shared state cache, and adds Kev-specific resource limits.
50%UnverifiedOpen-source projects attempting to replicate Jev's capabilities include nano Jeff, a project formerly known as open Jeff, and a family of micro decision models named Kev.
50%UnverifiedLaya, Kev, and Ollaya are three open-source alternatives frequently mentioned in the context of Jev.
50%UnverifiedAcross three option orderings combined, Kev scored 74/90 and Laya scored 33/90; Kev had 4 messages and Laya had 5 messages where results changed with the option order.
50%UnverifiedFor the policy-intensive customer service routing pilot task, Kev is a stronger starting point, while Laya is faster and has lower memory usage but requires improvement under these rules before it can be trusted.
50%UnverifiedIn cases requiring contextual understanding, Kev correctly handled the situation where a customer explicitly stated they did not want a refund and only needed a password reset by selecting technical support, while Laya incorrectly selected billing due to the presence of billing-related vocabulary.
50%UnverifiedKev is an open-source classification model based on Qwen 3.5's 0.8B base model, with LoRA fine-tuning weights merged in, using unidirectional reading and making decisions through a pointer head.
50%UnverifiedTested on the same machine equipped with a Spark CPU and limited to three threads, Laya's median call latency was 541 milliseconds and Kev's was 756 milliseconds, with the 95th percentile at approximately 607 and 802 milliseconds respectively.
50%UnverifiedUnder the original option order in the customer service ticket routing test, Kev scored 26/30 and Laya scored 12/30.
50%UnverifiedKev is a family of lightweight decision models built on Qwen3.5, positioned as "Jev-like" decision models.
50%UnverifiedOllama released the v0.40.4-rc1 pre-release, with the core change being the introduction of Kev decision scoring capability in the MLX backend.
50%UnverifiedKev is an open-source reproduction project built on Qwen 3.5, offering decision models in three sizes: 0.8B, 4B, and 9B.
50%