Compact open Llama base model for lightweight and on-device use
Specification
most-agreed values
Context
131K
Max output
131K
Released
2024-09-25
Knowledge cutoff
2023-12
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.10
Output
$0.10
Cache read
$0.10
Cache write
$0.10
Quality
3 benchmarks · 1 source
Composite
7th
percentile of 334 scored models
Rank
310 / 334
±0.10 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning7th2/4 bench
math3rd1/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| Chess Puzzles | 0.0 ±0.0 | default | Epoch AI | 2026-08-30 |
| OTIS Mock AIME 2024-2025 | 0.6 ±0.4 | default | Epoch AI | 2026-08-30 |
| GPQA diamond | 23.9 ±1.6 | default | Epoch AI | 2026-08-30 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 2 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| pioneer · meta-llama | $0.10 | $0.10 | $0.10 | $0.10 | 131K | 131K | — |
| vercel_ai_gateway · vercel-ai-gateway | $0.10 | $0.10 | — | — | 128K | 8K | — |
Other listings of this model
same model, different key
More from Meta
most-hosted first