Dataset updated 2026-10-31NVIDIA Nemotron 3.5 Bolt 74B-A9B
NVIDIA Nemotron 3.5 Bolt 74B-A9B is a 74B-parameter mixture-of-experts model (9B active per token). Listed, never ranked: its 2-bit build fits a Mac, and it needs 32GB of memory. None of its builds gets a speed estimate or a local verdict on a machine page.
- Parameters
- 74B(9B active)
- Format
- IQ2_XXS
- Min memory
- 32 GB
- Best for
- Agentic tasks, Tool calling, Vision
Which NVIDIA Nemotron 3.5 Bolt 74B-A9B builds fit a Mac?
| Build | Bits | Size | Fits |
|---|---|---|---|
| IQ2_XXS | 2 | 22.02 GB | 32GB Mac, ~0 GB to spare |
NVIDIA's vision-language MoE, released on Hugging Face on October 15, 2026 under OpenMDW-1.1: 74B total with 9B active per token and up to 256K tokens of context per the model card. NVIDIA ships it only as a native 2-bit build (experts in IQ2-XXS, Mamba layers in NVFP4, embedding and output in Q8_0). Ollama's library page says Apple Silicon / Metal is not currently supported for 74B-A9B.
Size = the build's GGUF files on Hugging Face. "Fits" = weights within the engine's model budget (about 435 GB on a 512GB Mac), before context and the vision projector. Why we never rank 2-bit quants · Hugging Face model card · NVIDIA Nemotron 3.5 Bolt on a Mac: 32GB for Text, 36GB With Vision
More Nemotron models
5 pagesGet told when a better model fits your MacBook Air M5 16 GB
Get one email when a new open-weight model is a better fit for this machine.
For: MacBook Air M5 16 GB
You'll also get the weekly ModelFit email. By signing up you agree to our Privacy Policy. Unsubscribe from either email anytime, in one click.
Frequently asked questions
Can I run NVIDIA Nemotron 3.5 Bolt 74B-A9B on a Mac?
From a Mac with 32GB of memory, which leaves about 22 GB for models. Builds that fit: nvidia's IQ2_XXS (22.02 GB, 2-bit). A 24GB Mac leaves about 17 GB, under the smallest build.
Why doesn't ModelFit rank NVIDIA Nemotron 3.5 Bolt 74B-A9B?
Its 2-bit builds are a class ModelFit never ranks. ModelFit lists the model with its build sizes, read from the Hugging Face file listings, and leaves its builds out of every local ranking, speed estimate and machine verdict.
Cite this page
ModelFit: NVIDIA Nemotron 3.5 Bolt 74B-A9B, specs, memory math and hardware verdicts. https://modelfit.io/models/nemotron-3.5-bolt-74b-a9b (dataset updated 2026-10-31, CC BY 4.0).