NVIDIA Nemotron 3 Super 120B A12B Base BF16 vs Ternary Bonsai 2 27B
At a Glance
| Compare |  Ternary Bonsai 2 27BPrismML | |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | Not reported | $0.075Openrouter ↗ · Sep 22, 2026 |
| Output priceFrom · USD / 1M tokens | Not reported | $0.50Openrouter ↗ · Sep 22, 2026 |
| Context windowMaximum documented tokens | 1,049K | 262K |
| 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 | NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16 | Ternary Bonsai 2 27B |
|---|---|---|
| Developer | NVIDIA | PrismML |
| Family | Nvidia Nemotron 3 Super 120b A12b Base Bf16 | Bonsai 2 |
| Model | NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16 | Ternary Bonsai 2 27B |
| Version | NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16 | Ternary Bonsai 2 27B |
| Lifecycle | active | active |
| Released | 2026-03-04 | 2026-09-17 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text, Image |
| Output modalities | Text | Text |
| Context window | 1,049K | 262K |
| Total parameters | 123.6B | 27.4B |
| Active parameters | 12B | Unknown |
| License | other | apache-2.0 |
| Open weights | Yes | Yes |
| API available | Unknown | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Unknown | Openrouter (Standard) |
| Capabilities | generation | 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 |
NVIDIA Nemotron 3 Super 120B A12B Base BF16 Capabilities
Ternary Bonsai 2 27B Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
| vs |  GPT-6 AstraOpenAI | cross-developer peerstext | |
Claude Fable 5.1Anthropic | vs | cross-developer peerstext | |
 Gemini 3.1 ProGoogle DeepMind | vs | cross-developer peerstext | |
 DeepSeek-V4.1-FlashDeepSeek | vs | cross-developer peerstext | |
| vs | Grok 4.6xAI | cross-developer peerstext | |
| vs |  Qwen3.8-MaxQwen | cross-developer peerstext | |
 Kimi-K3Moonshot AI | vs | cross-developer peerstext | |
 MiniMax-M3MiniMax | vs | cross-developer peerstext | |
| vs |  GLM-5.3Z.ai | cross-developer peerstext | |
| vs |  Hy4 previewTencent | cross-developer peerstext | |
Seed 2.1 ProByteDance Seed | vs | cross-developer peerstext | |
 Mistral Large 3Mistral AI | vs | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
NVIDIA Nemotron 3 Super 120B A12B Base BF16 vs Ternary Bonsai 2 27B FAQs
Is NVIDIA Nemotron 3 Super 120B A12B Base BF16 or Ternary Bonsai 2 27B better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both NVIDIA Nemotron 3 Super 120B A12B Base BF16 and Ternary Bonsai 2 27B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, NVIDIA Nemotron 3 Super 120B A12B Base BF16 or Ternary Bonsai 2 27B?+
Only Ternary Bonsai 2 27B has a directly sourced input price: $0.075 per million tokens. Only Ternary Bonsai 2 27B has a directly sourced output price: $0.50 per million tokens.
Which has a larger context window, NVIDIA Nemotron 3 Super 120B A12B Base BF16 or Ternary Bonsai 2 27B?+
NVIDIA Nemotron 3 Super 120B A12B Base BF16 has the larger sourced context window. NVIDIA Nemotron 3 Super 120B A12B Base BF16 supports 1,049K and Ternary Bonsai 2 27B supports 262K.
Which performs better in benchmarks, NVIDIA Nemotron 3 Super 120B A12B Base BF16 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 NVIDIA Nemotron 3 Super 120B A12B Base BF16 or Ternary Bonsai 2 27B be self-hosted?+
Both models have the same recorded self-hosting status: supported. NVIDIA Nemotron 3 Super 120B A12B Base BF16 is open weight; Ternary Bonsai 2 27B is open weight.
Can NVIDIA Nemotron 3 Super 120B A12B Base BF16 and Ternary Bonsai 2 27B understand images?+
NVIDIA Nemotron 3 Super 120B A12B Base BF16 is not 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, NVIDIA Nemotron 3 Super 120B A12B Base BF16 or Ternary Bonsai 2 27B?+
Neither has a larger sourced maximum output. NVIDIA Nemotron 3 Super 120B A12B Base BF16 is — and Ternary Bonsai 2 27B is —.
Do NVIDIA Nemotron 3 Super 120B A12B Base BF16 and Ternary Bonsai 2 27B support reasoning and tool use?+
NVIDIA Nemotron 3 Super 120B A12B Base BF16: none of these features are definitively sourced. Ternary Bonsai 2 27B: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, NVIDIA Nemotron 3 Super 120B A12B Base BF16 or Ternary Bonsai 2 27B?+
NVIDIA Nemotron 3 Super 120B A12B Base BF16 has 0 sourced provider routes; Ternary Bonsai 2 27B has 1, so Ternary Bonsai 2 27B has broader tracked availability.
Which offers better value, NVIDIA Nemotron 3 Super 120B A12B Base BF16 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.