Head to head
Inkling 2 Small vs Nemotron 3 Nano 30B-A3B.
Verdict by category, tale of the tape, shared benchmarks only, and cost at three workloads — all from the tracked data.
Verdict by category
| Category | Inkling 2 Small | Nemotron 3 Nano 30B-A3B | Winner |
|---|---|---|---|
| League Score | — | 0.0 | — |
| Coding (SWE-bench %) | — | — | — |
| Reasoning (GPQA %) | — | 73.0 | — |
| Context (tokens) | 262144 | 1000000 | Nemotron 3 Nano 30B-A3B |
| Speed (tok/s) | — | — | — |
Tale of the tape
| Spec | Inkling 2 Small | Nemotron 3 Nano 30B-A3B |
|---|---|---|
| Maker | Thinking Machines Lab | NVIDIA |
| Released | Nov 5, 2026 | Dec 15, 2025 |
| League Score | — | 0 |
| Context | 262,144 tokens | 1,000,000 tokens |
| Max output | — | — |
| $/1M input | — | — |
| $/1M output | — | — |
| Weights | Closed | Open |
| Speed | — | — |
Head-to-head benchmarks (shared only)
| Benchmark | Inkling 2 Small | Nemotron 3 Nano 30B-A3B |
|---|---|---|
| No shared benchmark measurements yet — shown as not measured, never interpolated. | ||
Cost at three workloads
| Workload | Inkling 2 Small | Nemotron 3 Nano 30B-A3B |
|---|---|---|
| Light — 1M in / 250K out | — | — |
| Standard — 10M in / 2.5M out | — | — |
| Long-context — 50M in / 5M out | — | — |
The pick
Pick Nemotron 3 Nano 30B-A3B if you need the bigger context window; you want downloadable weights / self-hosting.
All figures from the model database — sources and dates on each model page. Cost your own workload or compare a different pair.
Frequently asked questions
Which has the bigger context window, Inkling 2 Small or Nemotron 3 Nano 30B-A3B?
Nemotron 3 Nano 30B-A3B, with 1M of context against 262.1K for Inkling 2 Small.
Are Inkling 2 Small and Nemotron 3 Nano 30B-A3B open source?
Inkling 2 Small is closed weights — API access only; Nemotron 3 Nano 30B-A3B is open weights — it can be downloaded and self-hosted.