I used the 9B Instruct version, from the small models, it was the one with the best Latvian knowledge out there, bar none. GPT-OSS 20B and Qwen3 30B A3B and similar ones weren't even close.
That said, the model itself was a little bit dumb and not something you'd really use for programming/autocomplete or tool calling or anything like that, which also presented some problems - even for processing text, if you need RAG or tool server calls, you need to use something like Qwen3 for the actual logic and then pass the contents to EuroLLM for translation/formatting with the instructions, at which point your n8n workflow looks a bit messy and also you have to run those two models instead of only one.
Meanwhile, the best cloud model for Latvian that I've found so far was Google Gemini 2.5 Pro, but obviously can't use cloud models in certain on-prem use cases.
It seems there is some weird grouping of the language data which LLM cannot distinguish well. I wonder if it is the same for other similar languages like scandinavian or western slavic
I used the 9B Instruct version, from the small models, it was the one with the best Latvian knowledge out there, bar none. GPT-OSS 20B and Qwen3 30B A3B and similar ones weren't even close.
That said, the model itself was a little bit dumb and not something you'd really use for programming/autocomplete or tool calling or anything like that, which also presented some problems - even for processing text, if you need RAG or tool server calls, you need to use something like Qwen3 for the actual logic and then pass the contents to EuroLLM for translation/formatting with the instructions, at which point your n8n workflow looks a bit messy and also you have to run those two models instead of only one.
Meanwhile, the best cloud model for Latvian that I've found so far was Google Gemini 2.5 Pro, but obviously can't use cloud models in certain on-prem use cases.