$ diff ternary-bonsai-2-27b gemini-3-8-flash
Ternary Bonsai 2 27B vs Gemini 3.8 Flash
Values come from Ternary Bonsai 2 27B and Gemini 3.8 Flash, 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.
PrismmlTernary Bonsai 2 27B
- context
- 262K
- weights
- open
- $/M in
- —
- $/M out
- —
- context
- 1.0M
- weights
- closed
- $/M in
- $0.75
- $/M out
- $3.75
What actually differs
- Context window
- Gemini 3.8 Flash takes 1.0M against 262K — 4× more room in a single request.
- Weights
- Ternary Bonsai 2 27B publishes weights (Apache 2.0); Gemini 3.8 Flash is API-only. That decides self-hosting, air-gapped deployment and fine-tuning before any capability question does.
- Recency
- Ternary Bonsai 2 27B shipped 15 days after Gemini 3.8 Flash (2026-09-17 vs 2026-09-02).
Full spec
| Attribute | Ternary Bonsai 2 27B | Gemini 3.8 Flash |
|---|---|---|
| Developer | Prismml | Google DeepMind |
| Released | 2026-09-17 | 2026-09-02 |
| Context window | 262,144 | 1,048,576 tokens (65,536 max output) |
| Pricing | not recorded | $0.75/M input · $3.75/M output (introductory, through 2026-12-31) · $1.50/M · $7.50/M from 2027-01-01 |
| License | Apache 2.0 | proprietary |
| Availability | Hugging Face (`prism-ml/Ternary-Bonsai-2-27B-gguf`, `prism-ml/Ternary-Bonsai-2-27B-mlx-2bit`) | Gemini API, Google AI Studio, Antigravity, Android Studio, Gemini Enterprise / Gemini Enterprise Agent Platform |