Motif 3 motif-3
Motif-Technologies · motif-technologies
#9 overall
- params
- 314.8B
- arch
- moe
- license
- mit open weights
- released
- Aug 2026
- train compute
- 1.1e+24 FLOP
- downloads/30d
- 2.3k
# architecture
- layers
- 53
- d_model
- 4096
- heads
- 80q / 16kv
- head dim
- 192
- experts
- top-0 of 384 + 1 shared
- vocab
- 220160
- family
- Motif
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: #9 — score 90.0 ● low — a single signal; treat with caution
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.70 | 87.0 |
| bench_composite | 0.30 | 96.9 |
benchmark panel evidence:
| complete panel | score (0–100) |
|---|---|
| aa-coding-v1 | 96.9 |
Coding: provisional — score 86.8 ● 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_coding | 0.30 | 86.8 |
| aider_polyglot | 0.30 | — |
| swe_bench_verified | 0.40 | — |
missing signals are dropped and the remaining weights renormalized — never imputed.
# trend
methodology changed during this history window; score movement across that boundary is not model movement. See methodology v6.
# benchmarks
| benchmark | score | source | date |
|---|---|---|---|
| AA Coding Index | 63.5 | Artificial Analysis | — |
| AA Intelligence Index | 33.6 | Artificial Analysis | — |
# where to run
no known API providers — download the weights from Hugging Face and run them yourself.
source aliases
- epoch
Motif-3