$ diff embeddinggemma-2 ternary-bonsai-2-27b
EmbeddingGemma 2 vs Ternary Bonsai 2 27B
Values come from EmbeddingGemma 2 and Ternary Bonsai 2 27B, 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
- Ternary Bonsai 2 27B takes 262K against 8K — 32.8× more room in a single request.
- Weights
- Both publish weights — EmbeddingGemma 2 under Apache 2.0, Ternary Bonsai 2 27B under Apache 2.0. Check the licences rather than assuming they permit the same commercial use.
- Recency
- EmbeddingGemma 2 shipped 19 days after Ternary Bonsai 2 27B (2026-10-06 vs 2026-09-17).
Full spec
| Attribute | EmbeddingGemma 2 | Ternary Bonsai 2 27B |
|---|---|---|
| Developer | Google DeepMind | Prismml |
| Released | 2026-10-06 | 2026-09-17 |
| Context window | 8K tokens | 262,144 |
| Pricing | not recorded | not recorded |
| License | Apache 2.0 | Apache 2.0 |
| Availability | Weights on Hugging Face and Kaggle; local inference | Hugging Face (`prism-ml/Ternary-Bonsai-2-27B-gguf`, `prism-ml/Ternary-Bonsai-2-27B-mlx-2bit`) |