Granite 4.2 30B granite-4.2-30b

ibm-granite · ibm-granite

#26 overall

params
29.3B
arch
dense
license
apache-2.0 open weights
released
Aug 2026
downloads/30d
8.0k

# architecture

attn shared GQA 32q/8kv feed-forward (dense) every parameter, every token out ×64 layers 29.3B — no routing
layers
64
d_model
4096
heads
32q / 8kv
head dim
128
vocab
100352
family
granite

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: #26 — score 60.0 ● high — all signals present

signalweightinput (0–100)
aa_intelligence 0.70 54.6
bench_composite 0.30 72.5

benchmark panel evidence:

complete panelscore (0–100)
aime-2025-v172.5

Coding: provisional — score 33.3 ● 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_coding 0.30 33.3
aider_polyglot 0.30
swe_bench_verified 0.40

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

full methodology

# trend

OGM score · last 6 days
OGM score over 6 days
overall rank (up is better)
Overall rank over 6 days

# benchmarks

benchmarkscoresourcedate
AA Coding Index 29.9 Artificial Analysis
AA Intelligence Index 16.5 Artificial Analysis
AIME 2025 0.9 / 1 LLM Stats
Arena-hard-v2 0.7 / 1 LLM Stats
Bfcl-v4 0.6 / 1 LLM Stats
Bird-sql-(dev) 0.4 / 1 LLM Stats

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime
DeepInfra 128k $0.16$0.65 deepinfra 60

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
granite-4.2-30b