Current model · NVIDIA
Nemotron 3.5 Bolt 74B-A9B benchmarks, pricing and specs
Nemotron 3.5 Bolt 74B-A9B is a NVIDIA model released on October 15, 2026 that takes text, image and video input and produces text. Its price is not published and accepts up to 262,144 tokens of context.
- Context window
- 262K#55 of 64 current models
Data verified October 23, 2026 · Dataset 2026-10-23
Specs
Key facts
- Provider
- NVIDIA
- Model family
- Nemotron 3.5
- Release date
- October 15, 2026
- Status
- Current
- Access
- open weights
- API model id
- Not reported
- Context window
- 262,144 tokens
- Max output
- Not reported
- Input
- text, image, video
- Output
- text
- Task families
- text, multimodal
- Declared capabilities
- reasoning, agentic coding, image understanding, video understanding
Charts
Against every current text model
Where Nemotron 3.5 Bolt 74B-A9B lands among the current models of its task, on every independent benchmark, on price and on context.
Where it stands
Nemotron 3.5 Bolt 74B-A9B is no longer a current model, so it is not ranked; each bar is the share of today's text models its value beats. Each bar is the share of current models it beats.
Price and context
Context window
#55of 64
262K tokens · longer than 13%
Benchmarks
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. NVIDIA's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
No independent benchmark has published a result for Nemotron 3.5 Bolt 74B-A9B yet. It is still compared below on price, context and capabilities.
Fit
Strengths, cautions and best uses
- Strengths
- A 74B mixture-of-experts model with 9B active parameters, compressed from Nemotron 3.5 Super VL and natively quantized to 2 bits to fit in 24GB of memory
- NVIDIA reports 86.4% on GPQA Diamond and 51.0% on Terminal-Bench 2.1 for the 24GB build, ahead of Qwen3.6-35B-A3B on its own table
- Runs in llama.cpp, Ollama, LM Studio and vLLM on RTX PCs, RTX Spark laptops and DGX Spark, with up to 256K tokens of context
- Cautions
- Usable context depends on memory: the recipes in its model card use 64K tokens at 28GB and 256K at 32GB
- NVIDIA sells no per-token API for it, and no independent benchmark score is recorded here yet
- Best for
- Local agents on a single 24GB to 32GB GPU or laptop
- Private multimodal assistants that must run offline
From benchmark to production
Building on Nemotron 3.5 Bolt 74B-A9B?
Public scores rarely hold on your own data. We test it against the alternatives on your real tasks, then build the agent or pipeline around the model that wins.
Alternatives
Alternatives to Nemotron 3.5 Bolt 74B-A9B
The closest current text models by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
Muse Spark Open
- 1M context window vs 262K
- From Meta
Beam 1.0
- 1M context window vs 262K
- From Reflection AI
Muse Wonder
- 1.05M context window vs 262K
- From Meta
Mercury 3
- 1M context window vs 262K
- From Inception
Further reading
More on Nemotron 3.5 Bolt 74B-A9B
Other Nemotron 3.5 models
FAQ
Nemotron 3.5 Bolt 74B-A9B FAQ
What is the context window of Nemotron 3.5 Bolt 74B-A9B?
Nemotron 3.5 Bolt 74B-A9B accepts up to 262,144 tokens of context. That ranks #55 of 64 current text models by context length.
Is Nemotron 3.5 Bolt 74B-A9B open source or API only?
Nemotron 3.5 Bolt 74B-A9B is released as open weights that you can run yourself.
What are the best alternatives to Nemotron 3.5 Bolt 74B-A9B?
The closest current alternatives by price and measured performance are Muse Spark Open (1M context window vs 262K), Beam 1.0 (1M context window vs 262K), Muse Wonder (1.05M context window vs 262K) and Mercury 3 (1M context window vs 262K).
Sources
Sources
- NVIDIA Nemotron 3.5 Bolt 74B-A9B 24GB model card · NVIDIA · official · verified October 23, 2026
- NVIDIA expands Nemotron with Super VL and Bolt models · NVIDIA · official · verified October 23, 2026
Cite this page
Van Data Team. "Nemotron 3.5 Bolt 74B-A9B Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-23. https://vandatateam.com/ai-model-benchmarks/nemotron-3-5-bolt-74b-a9b
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether Nemotron 3.5 Bolt 74B-A9B fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls