kev vs gliner

Two of the top projects in Open models, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.

#77th of 117 in Open models

kev

Small decision models answering yes/no, choice and score questions over text

#1717th of 117 in Open models

gliner

Small zero-shot named entity recognition models with training and serving code

Verdict

kev ranks higher, 78 to 67. Of the 4 score parts we measure for both, kev leads on 2, gliner on 1 and 1 is even.

  • Adoptionkev leads by 27 points, 66 to 39: a wide gap.
  • FreshnessEven at 100.
  • Maintenancegliner leads by 1 point, 83 to 82: close to even.
  • Agent-readykev leads by 30 points, 30 to 0: a wide gap.

Pick kev if you are

Engineers routing or classifying text who want a self-hosted Jev-style API

  • Calibrated probabilities: each checkpoint ships with a fitted temperature
  • Works with the TypeSafe Python SDK unchanged via the /v1/systemone endpoint

Pick gliner if you are

Engineers needing local entity extraction or PII redaction without an LLM

  • Arbitrary entity labels at inference time, no labeled data needed
  • Runs on CPU; FP16, INT8, torch.compile and ONNX export available
kev vs gliner: score parts and facts
What we comparekevgliner
Score parts, out of 100
Adoption66, popular39, known
Freshness100, active100, active
Maintenance82, healthy83, healthy
Agent-ready30, minimal0, none
Facts from GitHub and the README
Stars10.1k4.3k
LicenseApache-2.0 (permissive)Apache-2.0 (permissive)
Last commitNov 2026Nov 2026
Last releaseOct 2026Nov 2026
LanguagePythonPython
DockerNoYes
GPUOptionalOptional
arm64 or Apple SiliconMentionedNot stated

kev

Kev is a family of four fine-tuned Qwen-based models (0.8B, 4B, 9B, 27B) that answer yes/no, multiple-choice and rating questions about a text and return calibrated probabilities. The server exposes an API matching TypeSafe's System One, so the TypeSafe Python SDK works against it. The repo includes training, evaluation and serving code, plus a Modal deploy script and fine-tuning skill.

Who it is for: Engineers routing or classifying text who want a self-hosted Jev-style API

Strengths

  • Calibrated probabilities: each checkpoint ships with a fitted temperature
  • Works with the TypeSafe Python SDK unchanged via the /v1/systemone endpoint
  • Four sizes; 0.8B runs on a 4 GB GPU, 27B scores within a point of Jev on new sources
  • Fine-tune from released checkpoints; about $1 for a Kev-4B run on a Modal H100

Weaknesses

  • Not on PyPI; install from source with uv, Python 3.12 or 3.13 only
  • Kev-27B is 51 GB of full weights and needs an 80 GB-class GPU
  • Trails Jev on harder knowledge tasks, e.g. MMLU-Pro 0.675 vs 0.840 for Kev-27B
  • Validated context is 8,192 tokens for 0.8B to 9B, despite a 65,536 server limit
  • GPU optional
  • Needs Modal (optional, for deploy and fine-tune skill), uv, Hugging Face Hub
  • Models: Kev-0.8B, Kev-4B, Kev-9B, Kev-27B, Qwen3.5 base
  • port 8009

gliner

GLiNER is a Python framework for training and running small transformer models that extract entities of any user-supplied label from text, without task-specific training. Variants cover bi-encoder label scaling, joint entity and relation extraction, streaming NER and PII detection. It runs on CPU, supports FP16/INT8 quantization, torch.compile and ONNX export, and includes a Ray Serve HTTP server.

Who it is for: Engineers needing local entity extraction or PII redaction without an LLM

Strengths

  • Arbitrary entity labels at inference time, no labeled data needed
  • Runs on CPU; FP16, INT8, torch.compile and ONNX export available
  • Several architectures: uni-encoder, bi-encoder, relation extraction, decoder, streaming
  • Includes fine-tuning script and Ray Serve server with dynamic batching

Weaknesses

  • Uni-encoder handles only about 50 entity types; more needs the bi-encoder
  • INT8 accuracy requires models trained with quantization-aware training
  • Classification, entity linking and schema extraction live in separate projects
  • Serving layer depends on Ray Serve, an extra install
  • GPU optional
  • Compose
  • Needs PyTorch, Ray Serve (optional, for serving)
  • Models: GLiNER uni-encoder, GLiNER bi-encoder, GLiNER RelEx, GLiNER Decoder, StreamingSpan
  • port 8000

More in Open models

Building with these?

We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.