Muse Glimmer 30B vs Ternary Bonsai 1.7B
At a Glance
| Compare | Muse Glimmer 30BMeta | Ternary Bonsai 1.7BPrismML |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $0.30Deepinfra ↗ · Sep 23, 2026 | Not reported |
| Output priceFrom · USD / 1M tokens | $1.20Deepinfra ↗ · Sep 23, 2026 | Not reported |
| Context windowMaximum documented tokens | 131K | 33K |
| Model facts checked | Sep 3, 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 | Muse Glimmer 30B | Ternary Bonsai 1.7B |
|---|---|---|
| Developer | Meta | PrismML |
| Family | Muse Glimmer | Bonsai 1 7b |
| Model | Muse Glimmer 30B | Ternary Bonsai 1.7B |
| Version | Muse Glimmer 30B | Ternary Bonsai 1.7B |
| Lifecycle | active | active |
| Released | 2026-08-09 | 2026-04-18 |
| Knowledge cutoff | 2026-01-04 | Unknown |
| Input modalities | Text, Image | Text |
| Output modalities | Text | Text |
| Context window | 131K | 33K |
| Total parameters | 29.8B | 1.7B |
| Active parameters | Unknown | Unknown |
| License | apache-2.0 | apache-2.0 |
| Open weights | Yes | Yes |
| API available | Yes | No |
| Self-hostable | Yes | Yes |
| Provider access | Deepinfra (Standard), Fireworks Ai (Standard), Together Ai (Standard) | Unknown |
| Capabilities | chat, generation, reasoning, structured_outputs, tools | chat, generation |
| Effective bit width | Unknown | 1.58 bits per weight |
| Weight size | Unknown | 0.46 GB |
| Weight format | Unknown | Ternary Q2_0 |
Muse Glimmer 30B Capabilities
Ternary Bonsai 1.7B Capabilities
Primary Evidence
Sources and Freshness
Questions
Muse Glimmer 30B vs Ternary Bonsai 1.7B FAQs
Is Muse Glimmer 30B or Ternary Bonsai 1.7B better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Muse Glimmer 30B and Ternary Bonsai 1.7B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Muse Glimmer 30B or Ternary Bonsai 1.7B?+
Only Muse Glimmer 30B has a directly sourced input price: $0.30 per million tokens. Only Muse Glimmer 30B has a directly sourced output price: $1.20 per million tokens.
Which has a larger context window, Muse Glimmer 30B or Ternary Bonsai 1.7B?+
Muse Glimmer 30B has the larger sourced context window. Muse Glimmer 30B supports 131K and Ternary Bonsai 1.7B supports 33K.
Which performs better in benchmarks, Muse Glimmer 30B 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 Muse Glimmer 30B or Ternary Bonsai 1.7B be self-hosted?+
Both models have the same recorded self-hosting status: supported. Muse Glimmer 30B is open weight; Ternary Bonsai 1.7B is open weight.
Can Muse Glimmer 30B and Ternary Bonsai 1.7B understand images?+
Muse Glimmer 30B 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, Muse Glimmer 30B or Ternary Bonsai 1.7B?+
Neither has a larger sourced maximum output. Muse Glimmer 30B is — and Ternary Bonsai 1.7B is —.
Do Muse Glimmer 30B and Ternary Bonsai 1.7B support reasoning and tool use?+
Muse Glimmer 30B: 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, Muse Glimmer 30B or Ternary Bonsai 1.7B?+
Muse Glimmer 30B has 3 sourced provider routes; Ternary Bonsai 1.7B has 0, so Muse Glimmer 30B has broader tracked availability.
Which offers better value, Muse Glimmer 30B 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.