LFM2.5-2.6B lfm-2.5-2.6b

LiquidAI · liquidai

unranked — no quality signals yet

params
2.7B
arch
dense
context
125k
license
other open weights
released
Jul 2026
downloads/30d
69.9k

# architecture

attn shared GQA 32q/8kv feed-forward (dense) every parameter, every token out ×30 layers ctx 128,000 2.7B — no routing
layers
30
d_model
2048
heads
32q / 8kv
head dim
64
vocab
128000
family
lfm2

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.

signalweightinput (0–100)
aa_intelligence 0.70 —
bench_composite 0.30 0.0

benchmark panel evidence:

complete panelscore (0–100)
aime-2025-v10.0

missing signals are dropped and the remaining weights renormalized — never imputed.

full methodology

# trend

OGM score · last 8 days
OGM score over 8 days
overall rank (up is better)
Overall rank over 8 days

# benchmarks

benchmarkscoresourcedate
Aa-omniscience-index -29.5 / 200 LLM Stats —
AIME 2025 0.5 / 1 LLM Stats —
Bfcl-v4 0.6 / 1 LLM Stats —
Claw-eval 0.6 / 1 LLM Stats —

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime✓
Liquidfp8 125k $0.35$0.50$0.04 via openrouter — 100.0%

sorted by blended price ((3·input + output) / 4 per 1M) · ✓ = the provider's own catalog confirms the offer · "via …" prices are what the aggregator routing the offer charges, not the provider's own list price

source aliases
llmstats
lfm-2.5-2.6b
openrouter
liquid/lfm-2.5-2.6b