Compare / Ternary Bonsai 2 27B vs Gemma 3 27B
Ternary Bonsai 2 27B vs Gemma 3 27B
Updated November 2026
Verdict
Ternary Bonsai 2 27B scores higher on the Small LM Index: 74.6 vs 32.7. On the 1 benchmark both labs report, Ternary Bonsai 2 27B wins 1 and Gemma 3 27B wins 0. Both need about 18.8 GB of memory at 4-bit quantization. Only Gemma 3 27B has a hosted API on OpenRouter ($0.10 per million tokens); the other has to be self-hosted.
Pick Ternary Bonsai 2 27B if…
- you want the strongest model overall
- you mostly write code
- you work with long documents
- you need a permissive license (Apache-2.0)
Pick Gemma 3 27B if…
- you want a hosted API rather than running it yourself
- you want the more widely used model (more quantized builds and community support)
Specifications
| Ternary Bonsai 2 27B | Gemma 3 27B | |
|---|---|---|
| Small LM Index | 74.6 (likely 72–77) | 32.7 (likely 26–41) |
| Lab | PrismML · United States | Google · United States |
| Released | 2026-09-17 | 2025-03-12 |
| Parameters | 27.4B (dense) | 27.4B (dense) |
| Memory at 4-bit | ~18.2 GB | ~18.8 GB |
| Context window | 262K tokens | 128K tokens |
| Input | text, image | text, image |
| Reasoning | Always thinks | No thinking |
| License | Apache-2.0 | Gemma |
| API price / 1M tokens | Self-host only | $0.10 ($0.080 in, $0.16 out) |
| Hugging Face downloads (30 days) | — | 359.4K |
Benchmarks
Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.
| Benchmark | Ternary Bonsai 2 27B | Gemma 3 27B |
|---|---|---|
| MMLU-Pro Knowledge | ≈ 86 | 67.5 |
| GPQA Diamond Knowledge | ≈ 85 | 42.4 |
| AIME Math | 95.8 | ≈ 39 |
| LiveCodeBench Coding | 90.1 | 29.7 |
| IFBench Instruction following | 74.0 | — |
| MMMU-Pro Vision | 75.5 | — |
| MMLU Knowledge | 89.1 | — |
| IFEval Instruction following | 91.3 | — |
| BFCL Agentic | 74.9 | — |
| MATH-500 Math | 98.8 | — |
Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.
Questions
Which is better, Ternary Bonsai 2 27B or Gemma 3 27B?
Ternary Bonsai 2 27B scores higher on the Small LM Index: 74.6 vs 32.7. On the 1 benchmark both labs report, Ternary Bonsai 2 27B wins 1 and Gemma 3 27B wins 0.
Which is cheaper to run?
Only Gemma 3 27B has a hosted API on OpenRouter ($0.10 per million tokens); the other has to be self-hosted. Both need about 18.8 GB of memory at 4-bit quantization.
Which has the longer context window?
Ternary Bonsai 2 27B has the longer context window: 262K tokens against 128K.
Can I use Ternary Bonsai 2 27B and Gemma 3 27B commercially?
Ternary Bonsai 2 27B is released under Apache-2.0 and Gemma 3 27B under Gemma. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.