$ diff embeddinggemma-2 ling-3-0-tiny
EmbeddingGemma 2 vs Ling-3.0-tiny
Values come from EmbeddingGemma 2 and Ling-3.0-tiny, where each is cited to its source. This page states no benchmark result and ranks neither model — it puts two published specifications next to each other. Where a lab has not published a figure, the row says so rather than guessing.
Google DeepMindEmbeddingGemma 2
- context
- 8K
- weights
- open
- $/M in
- —
- $/M out
- —
- context
- 262K
- weights
- open
- $/M in
- —
- $/M out
- —
What actually differs
- Context window
- Ling-3.0-tiny takes 262K against 8K — 32.8× more room in a single request.
- Weights
- Both publish weights — EmbeddingGemma 2 under Apache 2.0, Ling-3.0-tiny under MIT. Check the licences rather than assuming they permit the same commercial use.
- Recency
- EmbeddingGemma 2 shipped 61 days after Ling-3.0-tiny (2026-10-06 vs 2026-08-06).
Full spec
| Attribute | EmbeddingGemma 2 | Ling-3.0-tiny |
|---|---|---|
| Developer | Google DeepMind | Ant Group |
| Released | 2026-10-06 | 2026-08-06 |
| Context window | 8K tokens | 262k |
| Pricing | not recorded | not recorded |
| License | Apache 2.0 | MIT |
| Availability | Weights on Hugging Face and Kaggle; local inference | Hugging Face (BF16, FP8, INT4, GGUF), OpenRouter |