Gemini 3.6 Flash vs Ternary Bonsai 2 27B
At a Glance
| Compare |  Gemini 3.6 FlashGoogle DeepMind |  Ternary Bonsai 2 27BPrismML |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| IntelligenceHigher is better · MM Intelligence v2.5 | #19 of 4666.4 score · 3/3 sources · complete | UnrankedNot in the 46-model eligible cohort |
| CostLower is better · Published-token output estimate | #11 of 44$0.055 per LiveBench case | UnrankedNot in the 44-model eligible cohort |
| EfficiencyHigher is better · MM Efficiency v1.5 | #5 of 3863.7 score · 3/3 sources · complete | UnrankedNot in the 38-model eligible cohort |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $0.75Google AI ↗ · Aug 29, 2026 | $0.075Openrouter ↗ · Sep 22, 2026 |
| Output priceFrom · USD / 1M tokens | $3.75Google AI ↗ · Aug 29, 2026 | $0.50Openrouter ↗ · Sep 22, 2026 |
| Context windowMaximum documented tokens | 1,049K | 262K |
| Model facts checked | Aug 29, 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 | Gemini 3.6 Flash | Ternary Bonsai 2 27B |
|---|---|---|
| Developer | Google DeepMind | PrismML |
| Family | Gemini 3 | Bonsai 2 |
| Model | Gemini 3.6 Flash | Ternary Bonsai 2 27B |
| Version | Gemini 3.6 Flash | Ternary Bonsai 2 27B |
| Lifecycle | active | active |
| Released | Unknown | 2026-09-17 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image, Video, Audio, Document | Text, Image |
| Output modalities | Text | Text |
| Context window | 1,049K | 262K |
| Total parameters | Unknown | 27.4B |
| Active parameters | Unknown | Unknown |
| License | Unknown | apache-2.0 |
| Open weights | No | Yes |
| API available | Yes | Yes |
| Self-hostable | No | Yes |
| Provider access | Google AI (Standard), Google Gemini (Standard) | Openrouter (Standard) |
| Capabilities | chat, generation, reasoning, tools | chat, generation, reasoning, tools, vision |
| Base model | Unknown | Qwen3.8 27B |
| Effective bit width | Unknown | 1.76 bits per weight |
| Language model size | Unknown | 5.93 GB |
| Weight format | Unknown | Ternary g128 with FP16 group scales |
Gemini 3.6 Flash Capabilities
Ternary Bonsai 2 27B Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
Gemini 3.6 FlashGoogle DeepMind | vs |  GPT-6 AstraOpenAI | cross-developer peerstext |
Claude Fable 5.1Anthropic | vs | Gemini 3.6 FlashGoogle DeepMind | cross-developer peerstext |
Gemini 3.1 ProGoogle DeepMind | vs | Gemini 3.6 FlashGoogle DeepMind | family variantstext |
 DeepSeek-V4.1-FlashDeepSeek | vs | Gemini 3.6 FlashGoogle DeepMind | cross-developer peerstext |
Gemini 3.6 FlashGoogle DeepMind | vs | Grok 4.6xAI | cross-developer peerstext |
Gemini 3.6 FlashGoogle DeepMind | vs |  Qwen3.8-MaxQwen | cross-developer peerstext |
Gemini 3.6 FlashGoogle DeepMind | vs |  Kimi-K3Moonshot AI | cross-developer peerstext |
 MiniMax-M3MiniMax | vs | Gemini 3.6 FlashGoogle DeepMind | cross-developer peerstext |
Gemini 3.6 FlashGoogle DeepMind | vs |  GLM-5.3Z.ai | cross-developer peerstext |
Gemini 3.6 FlashGoogle DeepMind | vs |  Hy4 previewTencent | cross-developer peerstext |
Seed 2.1 ProByteDance Seed | vs | Gemini 3.6 FlashGoogle DeepMind | cross-developer peerstext |
Gemini 3.6 FlashGoogle DeepMind | vs |  Mistral Large 3Mistral AI | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
Gemini 3.6 Flash vs Ternary Bonsai 2 27B FAQs
Is Gemini 3.6 Flash or Ternary Bonsai 2 27B better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Gemini 3.6 Flash and Ternary Bonsai 2 27B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Gemini 3.6 Flash or Ternary Bonsai 2 27B?+
Gemini 3.6 Flash is $0.75 and Ternary Bonsai 2 27B is $0.075 per million tokens, so Ternary Bonsai 2 27B is cheaper on this metric. Gemini 3.6 Flash is $3.75 and Ternary Bonsai 2 27B is $0.50 per million tokens, so Ternary Bonsai 2 27B is cheaper on this metric.
Which has a larger context window, Gemini 3.6 Flash or Ternary Bonsai 2 27B?+
Gemini 3.6 Flash has the larger sourced context window. Gemini 3.6 Flash supports 1,049K and Ternary Bonsai 2 27B supports 262K.
Which performs better in benchmarks, Gemini 3.6 Flash or Ternary Bonsai 2 27B?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can Gemini 3.6 Flash or Ternary Bonsai 2 27B be self-hosted?+
Ternary Bonsai 2 27B is the only model in this pair currently marked as self-hostable. Gemini 3.6 Flash is not marked open weight; Ternary Bonsai 2 27B is open weight.
Can Gemini 3.6 Flash and Ternary Bonsai 2 27B understand images?+
Gemini 3.6 Flash is documented with image input; Ternary Bonsai 2 27B is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Gemini 3.6 Flash or Ternary Bonsai 2 27B?+
Neither has a larger sourced maximum output. Gemini 3.6 Flash is 66K and Ternary Bonsai 2 27B is —.
Do Gemini 3.6 Flash and Ternary Bonsai 2 27B support reasoning and tool use?+
Gemini 3.6 Flash: reasoning, tool calling, and image input. Ternary Bonsai 2 27B: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, Gemini 3.6 Flash or Ternary Bonsai 2 27B?+
Gemini 3.6 Flash has 2 sourced provider routes; Ternary Bonsai 2 27B has 1, so Gemini 3.6 Flash has broader tracked availability.
Which offers better value, Gemini 3.6 Flash or Ternary Bonsai 2 27B?+
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.