Bonsai Image Binary 4B vs Ternary Bonsai 1.7B
At a Glance
| Compare | Bonsai Image Binary 4BPrismML | Ternary Bonsai 1.7BPrismML |
|---|---|---|
| Pricing and Limits | ||
| Context windowMaximum documented tokens | Not reported | 33K |
| Model facts checked | Sep 18, 2026View model evidence → | Sep 18, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
Side-by-Side Facts
| Field | Bonsai Image Binary 4B | Ternary Bonsai 1.7B |
|---|---|---|
| Developer | PrismML | PrismML |
| Family | Bonsai Image 4b | Bonsai 1 7b |
| Model | Bonsai Image Binary 4B | Ternary Bonsai 1.7B |
| Version | Bonsai Image Binary 4B | Ternary Bonsai 1.7B |
| Lifecycle | active | active |
| Released | 2026-05-18 | 2026-04-18 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text |
| Output modalities | Image | Text |
| Context window | Unknown | 33K |
| Total parameters | 4B | 1.7B |
| Active parameters | Unknown | Unknown |
| License | apache-2.0 | apache-2.0 |
| Open weights | Yes | Yes |
| API available | No | No |
| Self-hostable | Yes | Yes |
| Provider access | Unknown | Unknown |
| Capabilities | generation | chat, generation |
| Base model | FLUX.2 Klein 4B | Unknown |
| Default resolution | 512 × 512 | Unknown |
| Effective bit width | Unknown | 1.58 bits per weight |
| Transformer size | 0.93 GB | Unknown |
| Weight size | Unknown | 0.46 GB |
| Weight format | Binary weights with FP16 group scales | Ternary Q2_0 |
Bonsai Image Binary 4B Capabilities
Ternary Bonsai 1.7B Capabilities
Primary Evidence
Sources and Freshness
Questions
Bonsai Image Binary 4B vs Ternary Bonsai 1.7B FAQs
Is Bonsai Image Binary 4B or Ternary Bonsai 1.7B better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Bonsai Image Binary 4B and Ternary Bonsai 1.7B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Bonsai Image Binary 4B or Ternary Bonsai 1.7B?+
Neither model has a directly sourced input price in this comparison. Neither model has a directly sourced output price in this comparison.
Which has a larger context window, Bonsai Image Binary 4B or Ternary Bonsai 1.7B?+
Neither model has a larger sourced context window in this comparison. Bonsai Image Binary 4B is — and Ternary Bonsai 1.7B is 33K.
Which performs better in benchmarks, Bonsai Image Binary 4B or Ternary Bonsai 1.7B?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can Bonsai Image Binary 4B or Ternary Bonsai 1.7B be self-hosted?+
Both models have the same recorded self-hosting status: supported. Bonsai Image Binary 4B is open weight; Ternary Bonsai 1.7B is open weight.
Can Bonsai Image Binary 4B and Ternary Bonsai 1.7B understand images?+
Bonsai Image Binary 4B is not documented with image input; Ternary Bonsai 1.7B is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Bonsai Image Binary 4B or Ternary Bonsai 1.7B?+
Neither has a larger sourced maximum output. Bonsai Image Binary 4B is — and Ternary Bonsai 1.7B is —.
Do Bonsai Image Binary 4B and Ternary Bonsai 1.7B support reasoning and tool use?+
Bonsai Image Binary 4B: none of these features are definitively sourced. Ternary Bonsai 1.7B: none of these features are definitively sourced. Feature support does not establish relative quality.
Which is available from more inference providers, Bonsai Image Binary 4B or Ternary Bonsai 1.7B?+
Bonsai Image Binary 4B has 0 sourced provider routes; Ternary Bonsai 1.7B has 0, a tie.
Which offers better value, Bonsai Image Binary 4B or Ternary Bonsai 1.7B?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.