Meltemi 7B
The first open large language model built for the Greek language.
About
Meltemi 7B is the first dedicated open LLM for Greek, developed by the Institute for Language and Speech Processing at Greece's Athena Research Center via continual pretraining of Mistral-7B on a 40-billion-token Greek corpus. Released under Apache 2.0 in both base and instruction-tuned variants with 8k context, it showed an average 14.9% improvement over Mistral-7B on ILSP's Greek evaluation suite.
Limitations: 7B scale caps absolute capability; evaluation gains are measured on ILSP's own benchmark suite, and Greek remains a low-resource language for downstream tooling.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 6/10
Scored 6/10 (metrics tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 67; Trending score 58/100 from researcher assessment.