Nomic Embed Text v2 MoE LATEST
A multilingual mixture-of-experts embedding model for search. Use search_query: and search_document: prefixes; its input limit is 512 tokens.
Exact local Ollama manifest and configuration checked on 2026-10-20. Memory figures are conservative planning estimates; no DeviceTerra inference or speed test is claimed. 512 tokens maximum. Use search_query: / search_document: prefixes. Generates vectors, not chat answers. Store the complete 0.475B weights; 0.305B active does not mean a 0.305B download. Embeddings return vectors, not chat answers.
- Official model source
- Official engine artifact
Will it run?
MamiLens uses 10 GB as a conservative planning floor for this profile and its listed quantization. This is not measured speed. Processor, backend support, context length, memory bandwidth and other applications still affect the result.
Check your complete system →What is it useful for?
Suggested Ollama artifact
Confirm the tag on the official page before downloading, then run:
ollama pull nomic-embed-text-v2-moe:latestStart with a representative non-sensitive task. Record the exact runtime, quantization, context, load time, generation speed, memory use and answer quality.
Evidence and limits
Published context: 512 token input limit. The source establishes specifications; it does not guarantee that maximum context fits at the MamiLens minimum RAM floor.