$ diff gemini-4-neon ternary-bonsai-2-27b
Gemini 4 Neon vs Ternary Bonsai 2 27B
Values come from Gemini 4 Neon 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 DeepMindGemini 4 Neon
- context
- 1M
- weights
- —
- $/M in
- $3
- $/M out
- $15
- context
- 262K
- weights
- open
- $/M in
- —
- $/M out
- —
What actually differs
- Context window
- Gemini 4 Neon takes 1M against 262K — 3.8× more room in a single request.
- Recency
- Gemini 4 Neon shipped 62 days after Ternary Bonsai 2 27B (2026-11-18 vs 2026-09-17).
Full spec
| Attribute | Gemini 4 Neon | Ternary Bonsai 2 27B |
|---|---|---|
| Developer | Google DeepMind | Prismml |
| Released | 2026-11-18 | 2026-09-17 |
| Context window | 1,000,000 tokens | 262,144 |
| Pricing | $3/M input · $15/M output · $0.15/M cached input | not recorded |
| License | not recorded | Apache 2.0 |
| Availability | Gemini API paid tier in Google AI Studio; Gemini for business; Google Antigravity and Gemini app for Google AI Pro/Ultra subscribers | Hugging Face (`prism-ml/Ternary-Bonsai-2-27B-gguf`, `prism-ml/Ternary-Bonsai-2-27B-mlx-2bit`) |