NVIDIA Nemotron 3.5 Lightning 30B A3B vs Inkling
Why this pair: Efficient open-weight mixture-of-experts models from NVIDIA and Thinking Machines Lab
Benchmark Performance
Available Benchmarks
| Benchmark | NVIDIA Nemotron 3.5 Lightning 30B-A3B | Inkling |
|---|---|---|
| LMArena Text Arenatext-2026-09-01-011508720696 · arena_rating · leader | 1,331.8493% of row best · rating · nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4; 95% CI [1322.39322537, 1341.28358716]; votes 4533; rank 207 | 1,438.25100% of row best · rating · inkling; 95% CI [1433.11517161, 1443.38005000]; votes 21973; rank 67 |
| Overall ResultCounted from the protocol-matched rows above | 0 benchmark wins | 1 benchmark winOverall lead |
Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.
Technical Differences
Side-by-Side Facts
| Field | NVIDIA Nemotron 3.5 Lightning 30B-A3B | Inkling |
|---|---|---|
| Developer | NVIDIA | Thinking Machines Lab |
| Family | Nvidia Nemotron 3 5 Lightning | Inkling |
| Model | NVIDIA Nemotron 3.5 Lightning 30B-A3B | Inkling |
| Version | NVIDIA Nemotron 3.5 Lightning 30B-A3B | Inkling |
| Lifecycle | active | active |
| Released | 2026-08-11 | 2026-07-15 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text, Image, Video, Audio |
| Output modalities | Text | Text |
| Context window | 1,049K | 1,049K |
| Total parameters | 30B | 975B |
| Active parameters | 3B | 41B |
| License | openmdw-1.1 | apache-2.0 |
| Open weights | Yes | Yes |
| API available | Yes | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Fireworks Ai (Standard) | Deepinfra (Standard), Fireworks Ai (Standard), Openrouter (Standard), Together Ai (Standard) |
| Capabilities | agents, chat, generation, reasoning, tools | agents, chat, coding, generation, reasoning, tools, vision |
17 comparable fields · 11 material differences · Editorially curated pair passes the primary-source comparison gate
NVIDIA Nemotron 3.5 Lightning 30B A3B Capabilities
Inkling Capabilities
Internal Comparison Graph
Related Comparisons
| A | Pair | B | Context |
|---|---|---|---|
| vs |  GPT-5.6 SolOpenAI | cross-developer peerstext | |
Claude Fable 5.1Anthropic | vs | cross-developer peerstext | |
 Gemini 3.1 ProGoogle DeepMind | vs | cross-developer peerstext | |
 DeepSeek-V4-ProDeepSeek | 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 3.5 Lightning 30B A3B vs Inkling FAQs
Is NVIDIA Nemotron 3.5 Lightning 30B A3B or Inkling better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both NVIDIA Nemotron 3.5 Lightning 30B A3B and Inkling, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, NVIDIA Nemotron 3.5 Lightning 30B A3B or Inkling?+
Only Inkling has a directly sourced input price: $0.95 per million tokens. Only Inkling has a directly sourced output price: $4.05 per million tokens.
Which has a larger context window, NVIDIA Nemotron 3.5 Lightning 30B A3B or Inkling?+
Neither model has a larger sourced context window in this comparison. NVIDIA Nemotron 3.5 Lightning 30B A3B is 1,049K and Inkling is 1,049K.
Which performs better in benchmarks, NVIDIA Nemotron 3.5 Lightning 30B A3B or Inkling?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can NVIDIA Nemotron 3.5 Lightning 30B A3B or Inkling be self-hosted?+
Both models have the same recorded self-hosting status: supported. NVIDIA Nemotron 3.5 Lightning 30B A3B is open weight; Inkling is open weight.
Can NVIDIA Nemotron 3.5 Lightning 30B A3B and Inkling understand images?+
NVIDIA Nemotron 3.5 Lightning 30B A3B is not documented with image input; Inkling is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, NVIDIA Nemotron 3.5 Lightning 30B A3B or Inkling?+
Neither has a larger sourced maximum output. NVIDIA Nemotron 3.5 Lightning 30B A3B is — and Inkling is —.
Do NVIDIA Nemotron 3.5 Lightning 30B A3B and Inkling support reasoning and tool use?+
NVIDIA Nemotron 3.5 Lightning 30B A3B: reasoning and tool calling. Inkling: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, NVIDIA Nemotron 3.5 Lightning 30B A3B or Inkling?+
NVIDIA Nemotron 3.5 Lightning 30B A3B has 1 sourced provider route; Inkling has 4, so Inkling has broader tracked availability.
Which offers better value, NVIDIA Nemotron 3.5 Lightning 30B A3B or Inkling?+
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.