K2 Horizon 0.9B k2-horizon-0.9b
IFM · ifm
unranked — no quality signals yet
- params
- 1.1B
- arch
- dense
- license
- apache-2.0 open weights
- released
- Sep 2026
- downloads/30d
- 11.2k
# architecture
- layers
- 28
- d_model
- 1536
- heads
- 32q / 8kv
- head dim
- 64
- vocab
- 64256
- family
- k2_horizon
signal path of one layer, generated from the registry's structured fields — dimension lines quote the model's real numbers; an MoE trace forks at the router, a dense trace runs straight through. Geometry fields come from the repo's config.json.
# why ranked
Overall: provisional — score — ● low — a single signal; treat with caution
provisional: too few independent signals for a numbered position — the score is shown, but this model sorts after every ranked model.
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.70 | — |
| bench_composite | 0.30 | 0.0 |
benchmark panel evidence:
| complete panel | score (0–100) |
|---|---|
| aime-2025-v1 | 0.0 |
| aime-2026-v1 | 0.0 |
missing signals are dropped and the remaining weights renormalized — never imputed.
# trend
collecting history — trends appear after a few daily runs.
# benchmarks
# where to run
no known API providers — download the weights from Hugging Face and run them yourself.
source aliases
- llmstats
k2-horizon-0.9b