K2 Horizon 3.7B
K2 Horizon 3.7B is the small dense member of IFM's (MBZUAI) fully open K2 Horizon family: a 3.7B-core decoder-only reasoning model (36 layers; about 5.1B parameters in the released safetensors including its 250K-token vocabulary embeddings) pretrained on 22.9T tokens, with a native 524,288-token (512K) context window from midtraining onward. Text in, text out, with per-request reasoning effort (high recommended) and JSON/XML tool-call formats. Released 2026-09-03 under Apache 2.0; on 2026-10-01 the main branch was updated to an anti-doom-loop (FTPO) checkpoint, and the model-card scores were refreshed on 2026-10-28 (they differ from the launch-blog figures). BF16 weights plus a GGUF build, intermediate checkpoints, training data, code, and logs. No priced provider is cataloged yet.
Key Specifications
Timeline
Technical Specifications
Benchmark Results
Model performance metrics across various tests and benchmarks
Programming
Reasoning
Other Tests
License & Metadata
Similar Models
All ModelsK2 Horizon 7B
Institute of Foundation Models
IBM Granite 4.0 Tiny Preview
IBM
Nemotron Labs Dory 1.0 (4B)
NVIDIA
LFM3-1.7B
Liquid AI
K2 Horizon 0.9B
Institute of Foundation Models
Llama 3.1 8B Instruct
Meta
IBM Granite 4.2 8B
IBM
Qwen2.5-Coder 7B Instruct
Alibaba
Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.