Ternary Bonsai 2 27B
prism-ml · released Sep 16, 2026 · prism-ml/Ternary-Bonsai-2-27B-gguf
- Type
- Open weightsApache License 2.0
- Params
- 27B
- Context
- 262K
about 197K words of context
Our take
Written Sep 24, 2026Ternary Bonsai 2 27B is a model you can download and run yourself, and it takes pictures alongside the question. Nothing we hold measures how good its answers are, and no licence is listed, so treat it as a trial rather than a settled choice.
Use it when you want to run the model on your own hardware, or when long documents would otherwise have to be split before they fit in a request. Two hosts serve it at the same rate, so if you would rather not run it yourself, either is a starting point. Skip it if you need measured evidence of quality before committing, or if you need to know the licence terms before building on it.
The case for it
- You can download it and run it on your own machine, so a host is an option rather than a requirement.
- Long documents go into a single request without being split first, though whether everything in them is recalled is unverified in our data.
- Text and images go in together, so a screenshot does not have to be described in words first.
The case against it
- No benchmark scores are supplied, so chat, coding and reasoning ability all need a trial on work you can judge yourself.
- No licence is listed, so what you are allowed to do with it commercially is unverified and needs checking at the source.
- Neither host carries a measured speed, so the matching rates cannot tell you which to pick.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 3.9 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 11.9 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 5.1 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.075 in / $0.50 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.075 / $0.50checked 4 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
| Darkbloomint4Through OpenRouter | $0.075 / $0.50checked 4 hours ago | 262K33K max reply | 23 tok/s | No | Yesunknown period | Unknown |
Across the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Darkbloomint4Through OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- prism-ml/Ternary-Bonsai-2-27B-gguf
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- prism-ml-ternary-bonsai-2-27b