---
title: "Can I Run Nemotron 3.5 Bolt 74B-A9B on a Mac? RAM & Speed"
canonical: https://llmcheck.net/can-i-run/nemotron-35-bolt-74b-a9b/
markdown: https://llmcheck.net/md/can-i-run/nemotron-35-bolt-74b-a9b.md
page_type: can-i-run
publisher: "LLMCheck (llmcheck.net)"
data_version: 2026-11-18
catalog_verified_through: 2026-11-18
updated: 2026-11-19
license: "CC BY 4.0"
license_url: https://creativecommons.org/licenses/by/4.0/
cite: "LLMCheck. (2026). Can I run Nemotron 3.5 Bolt 74B-A9B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/nemotron-35-bolt-74b-a9b/ (updated 2026-11-19). CC BY 4.0."
provenance:
  sourced: "Published figure — vendor or press review"
  community: "Linked individual run — blog, forum or submission"
  estimated: "Derived from published bandwidth model (https://llmcheck.net/methodology#estimation)"
---

# Can I run Nemotron 3.5 Bolt 74B-A9B on a Mac?

Markdown twin of https://llmcheck.net/can-i-run/nemotron-35-bolt-74b-a9b/, generated from the LLMCheck dataset (data version 2026-11-18) with the same figures as the page. Every speed names its provenance: **sourced** (a published vendor or press figure), **community** (one person's linked run) or **estimated** (the bandwidth model). LLMCheck is an index and runs no tests of its own. Licence CC BY 4.0: credit "LLMCheck (llmcheck.net)" and link the page.

On memory, yes: **Nemotron 3.5 Bolt 74B-A9B** fits 25 of 54 Macs in the LLMCheck index (runtime caveat below). It needs about **45 GB** at a 4K context, 46 GB at 64K. Smallest and cheapest current Mac at 15+ tok/s: the **Mac mini M5 Pro 48 GB** ($2,299, raised GPU limit). Best measured: **71.7 tok/s** on an M5 Max (community).

74B MoE, OpenMDW, by NVIDIA; minimum 45 GB of unified memory (weights plus a short context). It loads on 25 of the 54 Mac configurations the index ranks; 21 of them hold it within macOS's default GPU memory limit. Runtime caveat: Stock llama.cpp runs it from b11755, but NVIDIA's 24 GB GGUF falls back to the CPU on its NVFP4 layers (use a Q4_K_M file); Ollama does not support it on Apple Silicon (PR #19229) and stock mlx-lm cannot load it.

## Verdict for every Mac (54 configurations)

Verdicts: **Runs** = fits macOS's default GPU memory limit (at 15+ tok/s where the index has a figure); **Raise GPU limit** = fits the Mac's RAM, but needs more than macOS's default GPU memory limit; the command shown raises the limit until the next restart; **Doesn't fit** = does not load: the model's minimum RAM is above the Mac's, or it has no Mac runtime. Max context = the longest context that fits with a 16-bit KV cache (within the default limit, or the raised one where marked; an estimate from the model's config.json).

| Mac | Sold | Verdict | Build | tok/s | Provenance | Max context | Raise the limit | Model page |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| [MacBook Air M5 16 GB](https://llmcheck.net/best-llm/macbook-air-m5-16gb/) | current | Doesn't fit | — | — | — | — | — | — |
| [MacBook Air M5 24 GB](https://llmcheck.net/best-llm/macbook-air-m5-24gb/) | current | Doesn't fit | — | — | — | — | — | — |
| [MacBook Air M5 32 GB](https://llmcheck.net/best-llm/macbook-air-m5-32gb/) | current | Doesn't fit | — | — | — | — | — | — |
| [MacBook Air M1 8 GB](https://llmcheck.net/best-llm/macbook-air-m1-8gb/) | refurb | Doesn't fit | — | — | — | — | — | — |
| [MacBook Air M4 16 GB](https://llmcheck.net/best-llm/macbook-air-m4-16gb/) | used | Doesn't fit | — | — | — | — | — | — |
| [MacBook Air M2 16 GB](https://llmcheck.net/best-llm/macbook-air-m2-16gb/) | refurb | Doesn't fit | — | — | — | — | — | — |
| [MacBook Air M3 16 GB](https://llmcheck.net/best-llm/macbook-air-m3-16gb/) | refurb | Doesn't fit | — | — | — | — | — | — |
| [MacBook Air M1 16 GB](https://llmcheck.net/best-llm/macbook-air-m1-16gb/) | refurb | Doesn't fit | — | — | — | — | — | — |
| [MacBook Air M4 24 GB](https://llmcheck.net/best-llm/macbook-air-m4-24gb/) | used | Doesn't fit | — | — | — | — | — | — |
| [MacBook Air M2 24 GB](https://llmcheck.net/best-llm/macbook-air-m2-24gb/) | refurb | Doesn't fit | — | — | — | — | — | — |
| [MacBook Air M3 24 GB](https://llmcheck.net/best-llm/macbook-air-m3-24gb/) | refurb | Doesn't fit | — | — | — | — | — | — |
| [MacBook Pro M6 16 GB](https://llmcheck.net/best-llm/macbook-pro-m6-16gb/) | current | Doesn't fit | — | — | — | — | — | — |
| [MacBook Pro M5 Pro 24 GB](https://llmcheck.net/best-llm/macbook-pro-m5-pro-24gb/) | current | Doesn't fit | — | — | — | — | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m5-pro/ |
| [MacBook Pro M6 24 GB](https://llmcheck.net/best-llm/macbook-pro-m6-24gb/) | current | Doesn't fit | — | — | — | — | — | — |
| [MacBook Pro M6 32 GB](https://llmcheck.net/best-llm/macbook-pro-m6-32gb/) | current | Doesn't fit | — | — | — | — | — | — |
| [MacBook Pro M5 Pro 48 GB](https://llmcheck.net/best-llm/macbook-pro-m5-pro-48gb/) | current | Raise GPU limit | 4-bit | 31 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=43008` | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m5-pro/ |
| [MacBook Pro M5 Max 64 GB](https://llmcheck.net/best-llm/macbook-pro-m5-max-64gb/) | current | Runs | 4-bit | 58 | community | 256K (full window) | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m5-max/ |
| [MacBook Pro M5 Pro 64 GB](https://llmcheck.net/best-llm/macbook-pro-m5-pro-64gb/) | current | Runs | 4-bit | 31 | estimated | 256K (full window) | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m5-pro/ |
| [MacBook Pro M5 Max 128 GB](https://llmcheck.net/best-llm/macbook-pro-m5-max-128gb/) | current | Runs | 5-bit | 64 | community | 256K (full window) | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m5-max/ |
| [MacBook Pro M3 Max 64 GB](https://llmcheck.net/best-llm/macbook-pro-m3-max-64gb/) | refurb | Runs | 4-bit | 39 | estimated | 256K (full window) | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m3-max/ |
| [MacBook Pro M3 Max 128 GB](https://llmcheck.net/best-llm/macbook-pro-m3-max-128gb/) | refurb | Runs | 4-bit | 39 | estimated | 256K (full window) | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m3-max/ |
| [Mac mini M6 16 GB](https://llmcheck.net/best-llm/mac-mini-m6-16gb/) | current | Doesn't fit | — | — | — | — | — | — |
| [Mac mini M5 Pro 24 GB](https://llmcheck.net/best-llm/mac-mini-m5-pro-24gb/) | current | Doesn't fit | — | — | — | — | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m5-pro/ |
| [Mac mini M6 24 GB](https://llmcheck.net/best-llm/mac-mini-m6-24gb/) | current | Doesn't fit | — | — | — | — | — | — |
| [Mac mini M6 32 GB](https://llmcheck.net/best-llm/mac-mini-m6-32gb/) | current | Doesn't fit | — | — | — | — | — | — |
| [Mac mini M5 Pro 48 GB](https://llmcheck.net/best-llm/mac-mini-m5-pro-48gb/) | current | Raise GPU limit | 4-bit | 31 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=43008` | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m5-pro/ |
| [Mac mini M5 Pro 64 GB](https://llmcheck.net/best-llm/mac-mini-m5-pro-64gb/) | current | Runs | 4-bit | 31 | estimated | 256K (full window) | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m5-pro/ |
| [Mac mini M2 Pro 16 GB](https://llmcheck.net/best-llm/mac-mini-m2-pro-16gb/) | refurb | Doesn't fit | — | — | — | — | — | — |
| [Mac mini M4 16 GB](https://llmcheck.net/best-llm/mac-mini-m4-16gb/) | used | Doesn't fit | — | — | — | — | — | — |
| [Mac mini M4 Pro 24 GB](https://llmcheck.net/best-llm/mac-mini-m4-pro-24gb/) | used | Doesn't fit | — | — | — | — | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m4-pro/ |
| [Mac mini M4 24 GB](https://llmcheck.net/best-llm/mac-mini-m4-24gb/) | used | Doesn't fit | — | — | — | — | — | — |
| [Mac mini M2 Pro 32 GB](https://llmcheck.net/best-llm/mac-mini-m2-pro-32gb/) | refurb | Doesn't fit | — | — | — | — | — | — |
| [Mac mini M4 Pro 48 GB](https://llmcheck.net/best-llm/mac-mini-m4-pro-48gb/) | used | Raise GPU limit | Q4_K_M | 28 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=43008` | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m4-pro/ |
| [Mac mini M4 Pro 64 GB](https://llmcheck.net/best-llm/mac-mini-m4-pro-64gb/) | used | Runs | Q4_K_M | 28 | estimated | 256K (full window) | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m4-pro/ |
| [iMac M6 16 GB](https://llmcheck.net/best-llm/imac-m6-16gb/) | current | Doesn't fit | — | — | — | — | — | — |
| [iMac M6 24 GB](https://llmcheck.net/best-llm/imac-m6-24gb/) | current | Doesn't fit | — | — | — | — | — | — |
| [iMac M6 32 GB](https://llmcheck.net/best-llm/imac-m6-32gb/) | current | Doesn't fit | — | — | — | — | — | — |
| [Mac Studio M5 Max 36 GB](https://llmcheck.net/best-llm/mac-studio-m5-max-36gb/) | current | Doesn't fit | — | — | — | — | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m5-max/ |
| [Mac Studio M5 Max 48 GB](https://llmcheck.net/best-llm/mac-studio-m5-max-48gb/) | current | Raise GPU limit | Q4_K_M | 55 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=43008` | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m5-max/ |
| [Mac Studio M5 Max 64 GB](https://llmcheck.net/best-llm/mac-studio-m5-max-64gb/) | current | Runs | 4-bit | 58 | community | 256K (full window) | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m5-max/ |
| [Mac Studio M5 Ultra 96 GB](https://llmcheck.net/best-llm/mac-studio-m5-ultra-96gb/) | current | Runs | Q4_K_M | 79 | estimated | 256K (full window) | — | — |
| [Mac Studio M5 Max 128 GB](https://llmcheck.net/best-llm/mac-studio-m5-max-128gb/) | current | Runs | 5-bit | 64 | community | 256K (full window) | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m5-max/ |
| [Mac Studio M5 Ultra 256 GB](https://llmcheck.net/best-llm/mac-studio-m5-ultra-256gb/) | current | Runs | Q4_K_M | 79 | estimated | 256K (full window) | — | — |
| [Mac Studio M5 Ultra 512 GB](https://llmcheck.net/best-llm/mac-studio-m5-ultra-512gb/) | current | Runs | Q4_K_M | 79 | estimated | 256K (full window) | — | — |
| [Mac Studio M2 Max 32 GB](https://llmcheck.net/best-llm/mac-studio-m2-max-32gb/) | refurb | Doesn't fit | — | — | — | — | — | — |
| [Mac Studio M1 Ultra 64 GB](https://llmcheck.net/best-llm/mac-studio-m1-ultra-64gb/) | refurb | Runs | Q4_K_M | 55 | estimated | 256K (full window) | — | — |
| [Mac Studio M4 Max 64 GB](https://llmcheck.net/best-llm/mac-studio-m4-max-64gb/) | used | Runs | 4-bit | 52 | estimated | 256K (full window) | — | — |
| [Mac Studio M2 Max 64 GB](https://llmcheck.net/best-llm/mac-studio-m2-max-64gb/) | refurb | Runs | Q4_K_M | 39 | estimated | 256K (full window) | — | — |
| [Mac Studio M1 Ultra 128 GB](https://llmcheck.net/best-llm/mac-studio-m1-ultra-128gb/) | refurb | Runs | Q4_K_M | 55 | estimated | 256K (full window) | — | — |
| [Mac Studio M2 Ultra 128 GB](https://llmcheck.net/best-llm/mac-studio-m2-ultra-128gb/) | refurb | Runs | Q4_K_M | 55 | estimated | 256K (full window) | — | — |
| [Mac Studio M4 Max 128 GB](https://llmcheck.net/best-llm/mac-studio-m4-max-128gb/) | used | Runs | 4-bit | 52 | estimated | 256K (full window) | — | — |
| [Mac Studio M2 Ultra 192 GB](https://llmcheck.net/best-llm/mac-studio-m2-ultra-192gb/) | refurb | Runs | Q4_K_M | 55 | estimated | 256K (full window) | — | — |
| [Mac Studio M3 Ultra 256 GB](https://llmcheck.net/best-llm/mac-studio-m3-ultra-256gb/) | used | Runs | 4-bit | 57 | community | 256K (full window) | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m3-ultra/ |
| [Mac Studio M3 Ultra 512 GB](https://llmcheck.net/best-llm/mac-studio-m3-ultra-512gb/) | refurb | Runs | 4-bit | 57 | community | 256K (full window) | — | https://llmcheck.net/models/nemotron-35-bolt-74b-a9b-on-m3-ultra/ |

Provenance: **sourced** = Published figure — vendor or press review; **community** = Linked individual run — blog, forum or submission; **estimated** = Derived from published bandwidth model (https://llmcheck.net/methodology#estimation).

For large mixture-of-experts models (over 40B total), the formula’s typical error is about **34%** (the median gap to 70 measured plain-decode runs; it tends to undershoot (median −33%), and an estimate scaled from the model’s own measured run is usually closer; [method](https://llmcheck.net/methodology#typical-error)).

## Measured runs of Nemotron 3.5 Bolt 74B-A9B

| Chip | RAM | Runtime | Quant | tok/s | Provenance | Context | Date | Source | Flags |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| M3 Ultra | 512 GB | MLX | IQ2_XXS | 74.5 | community | 1k | 2026-10-18 | https://omlx.ai/benchmarks/performance/34w81zue | not an anchor |
| M3 Ultra | 256 GB | MLX | 4-bit | 56.5 | community | 1024-token prompt, 96 generated | 2026-10-15 | https://github.com/raullenchai/Rapid-MLX/blob/main/docs/engineering/performance/2026-10-15-nemotron-bolt-decode.md | — |
| M3 Ultra | 96 GB | llama.cpp | Q4_K_M | 41.61 | community | tg128 | 2026-10-16 | https://github.com/ggml-org/llama.cpp/issues/30610 | not an anchor |
| M5 Max | 64 GB | MLX | IQ2_XXS | 73 | community | 1k | 2026-10-23 | https://omlx.ai/benchmarks/performance/6hru2tuw | not an anchor |
| M5 Max | 128 GB | MLX | 4-bit | 71.7 | community | 128-token greedy sample | 2026-10-16 | https://huggingface.co/nativ-community/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-4bit | — |
| M5 Max | 128 GB | MLX | 5-bit | 63.6 | community | 64-token greedy sample | 2026-10-16 | https://huggingface.co/nativ-community/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-5bit | — |
| M5 Max | 128 GB | MLX | 4-bit | 57.9 | community | 4k | 2026-10-20 | https://omlx.ai/benchmarks/performance/ccadpy82 | — |
| M5 Max | 128 GB | MLX | 8-bit | 37 | community | — | 2026-10-15 | https://huggingface.co/divinetribe/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-8bit | not an anchor |
| M3 Max | 128 GB | MLX | IQ2_XXS | 50.8 | community | 1k | 2026-10-22 | https://omlx.ai/benchmarks/performance/5dykqndv | not an anchor |
| M3 Max | 128 GB | MLX | 4-bit | 44 | community | generation length not stated | 2026-10-16 | https://blog.bytebunkerlabs.ai/posts/nemotron-bolt-74b-on-a-mac/ | not an anchor |
| M5 Pro | 48 GB | MLX | IQ2_XXS | 39 | community | 512-token coding answers, median of 5 at T 0.6 | 2026-10-19 | https://github.com/nace-ai/kapitsa/blob/main/docs/benchmarks.md | not an anchor |
| M5 Pro | 64 GB | llama.cpp | IQ2_XXS + Q8_0 | 24.6 | community | random-text prompts, greedy, -c 262144 | 2026-10-16 | https://huggingface.co/UraionLabs/Nemotron-3.5-Bolt-74B-A9B-24GB-Metal-GGUF | not an anchor |
| M4 Pro | 48 GB | MLX | IQ2_XXS | 34.6 | community | 512-token coding answers, median of 5 at T 0.6 | 2026-10-19 | https://github.com/nace-ai/kapitsa/blob/main/docs/benchmarks.md | not an anchor |

One row is one measurement session; on each chip the verdict table shows the lower median of the eligible runs (plain decode at 5 bits or fewer). A binned or not-an-anchor run is shown but never used as a reference.

## Run it

No verified Ollama tag in the index; start from the listing: https://huggingface.co/nativ-community/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-5bit

Model card: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16


## Cite this page

LLMCheck. (2026). Can I run Nemotron 3.5 Bolt 74B-A9B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/nemotron-35-bolt-74b-a9b/ (updated 2026-11-19). CC BY 4.0.

How to cite: https://llmcheck.net/cite · Open data (CSV, JSON): https://llmcheck.net/data/ · Every Markdown mirror: https://llmcheck.net/md/index.md
