$ diff ternary-bonsai-2-27b claude-fable-5-1
Ternary Bonsai 2 27B vs Claude Fable 5.1
Values come from Ternary Bonsai 2 27B and Claude Fable 5.1, 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
- 1M
- weights
- closed
- $/M in
- $10
- $/M out
- $50
What actually differs
- Context window
- Claude Fable 5.1 takes 1M against 262K — 3.8× more room in a single request.
- Weights
- Ternary Bonsai 2 27B publishes weights (Apache 2.0); Claude Fable 5.1 is API-only. That decides self-hosting, air-gapped deployment and fine-tuning before any capability question does.
- Recency
- Ternary Bonsai 2 27B shipped 16 days after Claude Fable 5.1 (2026-09-17 vs 2026-09-01).
Full spec
| Attribute | Ternary Bonsai 2 27B | Claude Fable 5.1 |
|---|---|---|
| Developer | Prismml | Anthropic |
| Released | 2026-09-17 | 2026-09-01 |
| Context window | 262,144 | 1M tokens |
| Pricing | not recorded | $10/M input · $50/M output · cache reads $0.25/M |
| License | Apache 2.0 | proprietary (API-only; no weight release) |
| Availability | Hugging Face (`prism-ml/Ternary-Bonsai-2-27B-gguf`, `prism-ml/Ternary-Bonsai-2-27B-mlx-2bit`) | Claude API as `claude-fable-5-1`; plan-tier access is disputed — see `## Conflicting Reports` |