Qwen3.5 397B A17B vs Ternary Bonsai 1.7B
At a Glance
| Compare | Ternary Bonsai 1.7BPrismML | |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $0.45Deepinfra ↗ · Sep 21, 2026 | Not reported |
| Output priceFrom · USD / 1M tokens | $3.00Deepinfra ↗ · Sep 21, 2026 | Not reported |
| Context windowMaximum documented tokens | 262K | 33K |
| Model facts checked | Aug 28, 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 | Qwen3.5-397B-A17B | Ternary Bonsai 1.7B |
|---|---|---|
| Developer | Qwen | PrismML |
| Family | Qwen3 5 397b A17b | Bonsai 1 7b |
| Model | Qwen3.5-397B-A17B | Ternary Bonsai 1.7B |
| Version | Qwen3.5-397B-A17B | Ternary Bonsai 1.7B |
| Lifecycle | active | active |
| Released | 2026-02-15 | 2026-04-18 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image | Text |
| Output modalities | Text | Text |
| Context window | 262K | 33K |
| Total parameters | 403.4B | 1.7B |
| Active parameters | 17B | Unknown |
| License | apache-2.0 | apache-2.0 |
| Open weights | Yes | Yes |
| API available | Yes | No |
| Self-hostable | Yes | Yes |
| Provider access | Deepinfra (Standard), Hugging Face (Standard), Openrouter (Standard), Together Ai (Standard) | Unknown |
| Capabilities | chat, generation, reasoning, tools | chat, generation |
| Effective bit width | Unknown | 1.58 bits per weight |
| Weight size | Unknown | 0.46 GB |
| Weight format | Unknown | Ternary Q2_0 |
Qwen3.5 397B A17B Capabilities
Ternary Bonsai 1.7B Capabilities
Primary Evidence
Sources and Freshness
Questions
Qwen3.5 397B A17B vs Ternary Bonsai 1.7B FAQs
Is Qwen3.5 397B A17B or Ternary Bonsai 1.7B better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Qwen3.5 397B A17B and Ternary Bonsai 1.7B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Qwen3.5 397B A17B or Ternary Bonsai 1.7B?+
Only Qwen3.5 397B A17B has a directly sourced input price: $0.45 per million tokens. Only Qwen3.5 397B A17B has a directly sourced output price: $3.00 per million tokens.
Which has a larger context window, Qwen3.5 397B A17B or Ternary Bonsai 1.7B?+
Qwen3.5 397B A17B has the larger sourced context window. Qwen3.5 397B A17B supports 262K and Ternary Bonsai 1.7B supports 33K.
Which performs better in benchmarks, Qwen3.5 397B A17B 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 Qwen3.5 397B A17B or Ternary Bonsai 1.7B be self-hosted?+
Both models have the same recorded self-hosting status: supported. Qwen3.5 397B A17B is open weight; Ternary Bonsai 1.7B is open weight.
Can Qwen3.5 397B A17B and Ternary Bonsai 1.7B understand images?+
Qwen3.5 397B A17B is 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, Qwen3.5 397B A17B or Ternary Bonsai 1.7B?+
Neither has a larger sourced maximum output. Qwen3.5 397B A17B is — and Ternary Bonsai 1.7B is —.
Do Qwen3.5 397B A17B and Ternary Bonsai 1.7B support reasoning and tool use?+
Qwen3.5 397B A17B: reasoning, tool calling, and image input. 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, Qwen3.5 397B A17B or Ternary Bonsai 1.7B?+
Qwen3.5 397B A17B has 4 sourced provider routes; Ternary Bonsai 1.7B has 0, so Qwen3.5 397B A17B has broader tracked availability.
Which offers better value, Qwen3.5 397B A17B 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.