Gemini 3.8 Flash vs Ternary Bonsai 8B
At a Glance
| Compare |  Gemini 3.8 FlashGoogle DeepMind |  Ternary Bonsai 8BPrismML |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| IntelligenceHigher is better · MM Intelligence v2.5 | #8 of 4682.0 score · 2/3 sources · provisional · missing ARC-AGI-2 · full-core range 54.7–88.0 | UnrankedNot in the 46-model eligible cohort |
| CostLower is better · Published-token output estimate | #26 of 44$0.160 per LiveBench case | UnrankedNot in the 44-model eligible cohort |
| EfficiencyHigher is better · MM Efficiency v1.5 | #8 of 3860.4 score · 2/3 sources · provisional · missing ARC-AGI-2 · full-core range 46.7–63.4 | UnrankedNot in the 38-model eligible cohort |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $0.75Google AI ↗ · Sep 2, 2026 | Not reported |
| Output priceFrom · USD / 1M tokens | $3.75Google AI ↗ · Sep 2, 2026 | Not reported |
| Context windowMaximum documented tokens | 1,049K | 66K |
| Model facts checked | Sep 2, 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 3.8 Flash | Ternary Bonsai 8B |
|---|---|---|
| Developer | Google DeepMind | PrismML |
| Family | Gemini 3 | Bonsai 8b |
| Model | Gemini 3.8 Flash | Ternary Bonsai 8B |
| Version | Gemini 3.8 Flash | Ternary Bonsai 8B |
| Lifecycle | active | active |
| Released | 2026-09-02 | 2026-04-18 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image, Video, Audio, Document | Text |
| Output modalities | Text | Text |
| Context window | 1,049K | 66K |
| Total parameters | Unknown | 8.2B |
| Active parameters | Unknown | Unknown |
| License | Unknown | apache-2.0 |
| Open weights | No | Yes |
| API available | Yes | No |
| Self-hostable | No | Yes |
| Provider access | Google AI (Standard), Google Gemini (Standard) | Unknown |
| Capabilities | chat, code_execution, computer_use, generation, reasoning, structured_outputs, tools | chat, generation |
| Effective bit width | Unknown | 1.58 bits per weight |
| Weight size | Unknown | 2.18 GB |
| Weight format | Unknown | Ternary Q2_0 |
Gemini 3.8 Flash Capabilities
Ternary Bonsai 8B Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
Gemini 3.7 FlashGoogle DeepMind | vs | Gemini 3.8 FlashGoogle DeepMind | family variantstext |
Gemini 3.8 FlashGoogle DeepMind | vs |  GPT-6 AstraOpenAI | cross-developer peerstext |
Claude Fable 5.1Anthropic | vs | Gemini 3.8 FlashGoogle DeepMind | cross-developer peerstext |
Gemini 3.1 ProGoogle DeepMind | vs | Gemini 3.8 FlashGoogle DeepMind | family variantstext |
 DeepSeek-V4.1-FlashDeepSeek | vs | Gemini 3.8 FlashGoogle DeepMind | cross-developer peerstext |
Gemini 3.8 FlashGoogle DeepMind | vs | Grok 4.6xAI | cross-developer peerstext |
Gemini 3.8 FlashGoogle DeepMind | vs |  Qwen3.8-MaxQwen | cross-developer peerstext |
Gemini 3.8 FlashGoogle DeepMind | vs |  Kimi-K3Moonshot AI | cross-developer peerstext |
 MiniMax-M3MiniMax | vs | Gemini 3.8 FlashGoogle DeepMind | cross-developer peerstext |
Gemini 3.8 FlashGoogle DeepMind | vs |  GLM-5.3Z.ai | cross-developer peerstext |
Gemini 3.8 FlashGoogle DeepMind | vs |  Hy4 previewTencent | cross-developer peerstext |
Seed 2.1 ProByteDance Seed | vs | Gemini 3.8 FlashGoogle DeepMind | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
Gemini 3.8 Flash vs Ternary Bonsai 8B FAQs
Is Gemini 3.8 Flash or Ternary Bonsai 8B better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Gemini 3.8 Flash and Ternary Bonsai 8B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Gemini 3.8 Flash or Ternary Bonsai 8B?+
Only Gemini 3.8 Flash has a directly sourced input price: $0.75 per million tokens. Only Gemini 3.8 Flash has a directly sourced output price: $3.75 per million tokens.
Which has a larger context window, Gemini 3.8 Flash or Ternary Bonsai 8B?+
Gemini 3.8 Flash has the larger sourced context window. Gemini 3.8 Flash supports 1,049K and Ternary Bonsai 8B supports 66K.
Which performs better in benchmarks, Gemini 3.8 Flash or Ternary Bonsai 8B?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can Gemini 3.8 Flash or Ternary Bonsai 8B be self-hosted?+
Ternary Bonsai 8B is the only model in this pair currently marked as self-hostable. Gemini 3.8 Flash is not marked open weight; Ternary Bonsai 8B is open weight.
Can Gemini 3.8 Flash and Ternary Bonsai 8B understand images?+
Gemini 3.8 Flash is documented with image input; Ternary Bonsai 8B is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Gemini 3.8 Flash or Ternary Bonsai 8B?+
Neither has a larger sourced maximum output. Gemini 3.8 Flash is 66K and Ternary Bonsai 8B is —.
Do Gemini 3.8 Flash and Ternary Bonsai 8B support reasoning and tool use?+
Gemini 3.8 Flash: reasoning, tool calling, and image input. Ternary Bonsai 8B: none of these features are definitively sourced. Feature support does not establish relative quality.
Which is available from more inference providers, Gemini 3.8 Flash or Ternary Bonsai 8B?+
Gemini 3.8 Flash has 2 sourced provider routes; Ternary Bonsai 8B has 0, so Gemini 3.8 Flash has broader tracked availability.
Which offers better value, Gemini 3.8 Flash or Ternary Bonsai 8B?+
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.