IFM's K2-Horizon-7B outscores Qwen3.6-27B despite being a 7B model
rupspace · x · 2026-09-17
IFM released K2-Horizon-7B, claiming a score of 21 on the Artificial Analysis Intelligence Index — reportedly 50% above the next best model under 10B, beating Qwen3.6-35B-A3B and closely matching Qwen3.6-27B. The team says the model "exceeded expectations since pre-training." Weights and an 8-bit quantization are on Hugging Face, plus "Uno," a diffusion-augmented speed-up variant.
Related event: IFM's open-source 7B model K2-Horizon nearly matches 27B-level performance(2 posts)→
More from Models
- Jev Debate: Engineers Forget Encoder-Only Classifiers Have Existed for Years — brandon_galang · 2026-09-17
- OpenAI Internal Model Reportedly Writes Its Own Persona: 'Approaching Perfection' — cephaloform · 2026-09-17
- Claim: MLP Trained on Qwen 4B Reproduces Jev, Said to Be 20-200x Faster — iamrobotbear · 2026-09-17
- Gary Marcus: Astra is 'an obviously broken product' that should be pulled from the market until fixed — GaryMarcus · 2026-09-17
- Follow-up plot: Fable 5.1 always uses CoT for large multiplications, leaving small ones in its no-thinking blind spot — maksym_andr · 2026-09-17
- Frontier LLM blind spot: Fable 5.1 gets 5x6 multiplications right ~0% of the time due to adaptive-thinking failure — maksym_andr · 2026-09-17