K2 V2 k2-v2

IFM · ifm

#69 overall

params
—
arch
dense
license
apache-2.0 open weights
released
Dec 2025
downloads/30d
540

# architecture

attn shared GQA 64q/8kv feed-forward (dense) every parameter, every token out ×80 layers
layers
80
d_model
8192
heads
64q / 8kv
head dim
128
vocab
250112
family
llama

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: #69 — score 37.0 ● low — a single signal; treat with caution

signalweightinput (0–100)
aa_intelligence 0.70 32.9
bench_composite 0.30 46.4

benchmark panel evidence:

complete panelscore (0–100)
aa-math-v146.4

full methodology

# trend

OGM score · last 52 days
OGM score over 52 days
overall rank (up is better)
Overall rank over 52 days

methodology changed during this history window; score movement across that boundary is not model movement. See methodology v6.

# benchmarks

benchmarkscoresourcedate
AA Intelligence Index 9.9 Artificial Analysis —
AA Math Index 78.3 Artificial Analysis —

# where to run

no known API providers — download the weights from Hugging Face and run them yourself.

source aliases
aa
k2-v2