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

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).

Mac 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.

RAM at 4K
45
GB
RAM at 64K
46
GB, 16-bit KV
Macs that run it
25
of 54 configs
Best measured
community71.7
tok/s · M5 Max

Nemotron 3.5 Bolt 74B-A9B on every Mac

One row per Mac configuration, grouped by product line. The build is the one each speed is for; the context column is the longest prompt that fits inside macOS’s default GPU memory limit with a 16-bit KV cache (“raised” where the limit has to be raised first; “full” when the whole window fits). Speeds are decode tok/s from the LLMCheck index, each with its provenance mark. 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).

Runs fits macOS’s default GPU limit, 15+ tok/sRuns, slowly fits, under 15 tok/sRaise GPU limit fits once the limit is raised (command below)Doesn't fit needs more memory than the Mac has
MacVerdictBuildSpeedMax contextModel page
MacBook Air
MacBook Air M5 16 GBDoesn't fit————
MacBook Air M5 24 GBDoesn't fit————
MacBook Air M5 32 GBDoesn't fit————
MacBook Air M1 8 GB refurbDoesn't fit————
MacBook Air M4 16 GB usedDoesn't fit————
MacBook Air M2 16 GB refurbDoesn't fit————
MacBook Air M3 16 GB refurbDoesn't fit————
MacBook Air M1 16 GB refurbDoesn't fit————
MacBook Air M4 24 GB usedDoesn't fit————
MacBook Air M2 24 GB refurbDoesn't fit————
MacBook Air M3 24 GB refurbDoesn't fit————
MacBook Pro
MacBook Pro M6 16 GBDoesn't fit————
MacBook Pro M5 Pro 24 GBDoesn't fit————
MacBook Pro M6 24 GBDoesn't fit————
MacBook Pro M6 32 GBDoesn't fit————
MacBook Pro M5 Pro 48 GBRaise GPU limit command ↓4-bitestimated31 tok/s—M5 Pro page
MacBook Pro M5 Max 64 GBRuns4-bitcommunity58 tok/s256K (full)M5 Max page
MacBook Pro M5 Pro 64 GBRuns4-bitestimated31 tok/s256K (full)M5 Pro page
MacBook Pro M5 Max 128 GBRuns5-bitcommunity64 tok/s256K (full)M5 Max page
MacBook Pro M3 Max 64 GB refurbRuns4-bitestimated39 tok/s256K (full)M3 Max page
MacBook Pro M3 Max 128 GB refurbRuns4-bitestimated39 tok/s256K (full)M3 Max page
Mac mini
Mac mini M6 16 GBDoesn't fit————
Mac mini M5 Pro 24 GBDoesn't fit————
Mac mini M6 24 GBDoesn't fit————
Mac mini M6 32 GBDoesn't fit————
Mac mini M5 Pro 48 GBRaise GPU limit command ↓4-bitestimated31 tok/s—M5 Pro page
Mac mini M5 Pro 64 GBRuns4-bitestimated31 tok/s256K (full)M5 Pro page
Mac mini M2 Pro 16 GB refurbDoesn't fit————
Mac mini M4 16 GB usedDoesn't fit————
Mac mini M4 Pro 24 GB usedDoesn't fit————
Mac mini M4 24 GB usedDoesn't fit————
Mac mini M2 Pro 32 GB refurbDoesn't fit————
Mac mini M4 Pro 48 GB usedRaise GPU limit command ↓Q4_K_Mestimated28 tok/s—M4 Pro page
Mac mini M4 Pro 64 GB usedRunsQ4_K_Mestimated28 tok/s256K (full)M4 Pro page
iMac
iMac M6 16 GBDoesn't fit————
iMac M6 24 GBDoesn't fit————
iMac M6 32 GBDoesn't fit————
Mac Studio
Mac Studio M5 Max 36 GBDoesn't fit————
Mac Studio M5 Max 48 GBRaise GPU limit command ↓Q4_K_Mestimated55 tok/s—M5 Max page
Mac Studio M5 Max 64 GBRuns4-bitcommunity58 tok/s256K (full)M5 Max page
Mac Studio M5 Ultra 96 GBRunsQ4_K_Mestimated79 tok/s256K (full)—
Mac Studio M5 Max 128 GBRuns5-bitcommunity64 tok/s256K (full)M5 Max page
Mac Studio M5 Ultra 256 GBRunsQ4_K_Mestimated79 tok/s256K (full)—
Mac Studio M5 Ultra 512 GBRunsQ4_K_Mestimated79 tok/s256K (full)—
Mac Studio M2 Max 32 GB refurbDoesn't fit————
Mac Studio M1 Ultra 64 GB refurbRunsQ4_K_Mestimated55 tok/s256K (full)—
Mac Studio M4 Max 64 GB usedRuns4-bitestimated52 tok/s256K (full)—
Mac Studio M2 Max 64 GB refurbRunsQ4_K_Mestimated39 tok/s256K (full)—
Mac Studio M1 Ultra 128 GB refurbRunsQ4_K_Mestimated55 tok/s256K (full)—
Mac Studio M2 Ultra 128 GB refurbRunsQ4_K_Mestimated55 tok/s256K (full)—
Mac Studio M4 Max 128 GB usedRuns4-bitestimated52 tok/s256K (full)—
Mac Studio M2 Ultra 192 GB refurbRunsQ4_K_Mestimated55 tok/s256K (full)—
Mac Studio M3 Ultra 256 GB usedRuns4-bitcommunity57 tok/s256K (full)M3 Ultra page
Mac Studio M3 Ultra 512 GB refurbRuns4-bitcommunity57 tok/s256K (full)M3 Ultra page
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Context memory is computed from its config.json (hybrid Mamba-2: attention on 8 of 88 layers; Mamba layers keep a constant state): about 0.5 GB of 16-bit KV cache at 64K tokens. A q8 cache (llama.cpp -ctk q8_0 -ctv q8_0, Ollama OLLAMA_KV_CACHE_TYPE=q8_0) halves that part. Runtimes also grow a compute buffer with context, so a fit within about 1 GB of the limit is optimistic.

Raising the GPU memory limit

macOS lets the GPU wire only part of unified memory by default (Metal’s recommended working set; M5 and M6 Macs run macOS 26 or later, whose default is higher), and Nemotron 3.5 Bolt 74B-A9B needs about 45 GB. On the Macs marked Raise GPU limit it fits in RAM but not inside that default. The default is a performance threshold, not a hard wall: past it, the runtime moves part of it to the CPU or shortens the context (llama.cpp, Ollama), runs it slowly (MLX), or stops with an out-of-memory error. One command raises the limit until the next restart (sudo sysctl iogpu.wired_limit_mb=0 restores the default sooner); it leaves macOS a reserve, and other apps get less memory while the model is loaded.

Nemotron 3.5 Bolt 74B-A9B: memory by quantization

Weights are 74B parameters at each format’s effective size (the index’s GB-per-billion table), plus about 2 GB for the runtime and a short context; longer contexts add the KV cache computed from the model’s config.json at 16 bits. It is a mixture-of-experts model: all 74B parameters sit in memory although only 9B are read per token. The first row is the catalog’s own figure (about 45 GB at a 4K context), the one every verdict on this page uses. “Smallest Mac” is the smallest memory size among the Macs Apple sells new that holds it at a 4K context inside that Mac’s default GPU limit. Estimates, not measurements.

BuildWeightsRAM at 4Kat 32Kat 64KSmallest Mac
As catalogued—45 GB45 GB46 GB64 GB
Q2_K25.2 GB27 GB27 GB28 GB36 GB (32 GB with a raised limit)
Q3_K_M36.3 GB38 GB38 GB39 GB64 GB (48 GB with a raised limit)
Q4_K_M42.2 GB44 GB44 GB45 GB64 GB
Q5_K_M52.5 GB55 GB55 GB55 GB96 GB (64 GB with a raised limit)
Q6_K60.7 GB63 GB63 GB63 GB96 GB
Q8_078.4 GB80 GB81 GB81 GB128 GB (96 GB with a raised limit)
F16148.0 GB150 GB150 GB151 GB256 GB

Measured runs of Nemotron 3.5 Bolt 74B-A9B

Every published (filled square) and community (hollow circle) run the index holds for Nemotron 3.5 Bolt 74B-A9B: 0 published, 13 community, each linked to its source. LLMCheck runs no tests of its own. One row is one measurement session; on each chip the table above shows the lower median of the eligible runs (plain decode at 5 bits or fewer), and a binned or “not an anchor” run is shown but never used as a reference.

ChipRuntimeQuantDecodeContextDateSource
M3 Ultra 512 GBMLXIQ2_XXScommunity74.5 tok/s1k2026-10-18omlx.ai not an anchor
M3 Ultra 256 GBMLX4-bitcommunity56.5 tok/s1024-token prompt, 96 generated2026-10-15github.com
M3 Ultra 96 GBllama.cppQ4_K_Mcommunity41.61 tok/stg1282026-10-16github.com not an anchor
M5 Max 64 GBMLXIQ2_XXScommunity73 tok/s1k2026-10-23omlx.ai not an anchor
M5 Max 128 GBMLX4-bitcommunity71.7 tok/s128-token greedy sample2026-10-16huggingface.co
M5 Max 128 GBMLX5-bitcommunity63.6 tok/s64-token greedy sample2026-10-16huggingface.co
M5 Max 128 GBMLX4-bitcommunity57.9 tok/s4k2026-10-20omlx.ai
M5 Max 128 GBMLX8-bitcommunity37 tok/s—2026-10-15huggingface.co not an anchor
M3 Max 128 GBMLXIQ2_XXScommunity50.8 tok/s1k2026-10-22omlx.ai not an anchor
M3 Max 128 GBMLX4-bitcommunity44 tok/sgeneration length not stated2026-10-16blog.bytebunkerlabs.ai not an anchor
M5 Pro 48 GBMLXIQ2_XXScommunity39 tok/s512-token coding answers, median of 5 at T 0.62026-10-19github.com not an anchor
M5 Pro 64 GBllama.cppIQ2_XXS + Q8_0community24.6 tok/srandom-text prompts, greedy, -c 2621442026-10-16huggingface.co not an anchor
M4 Pro 48 GBMLXIQ2_XXScommunity34.6 tok/s512-token coding answers, median of 5 at T 0.62026-10-19github.com not an anchor

Recommended setup

Before you start: 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.

The index has no verified Ollama tag for Nemotron 3.5 Bolt 74B-A9B. Start from its listing and copy the exact name of a build that fits: Hugging Face repo → · model card →

GGUF builds run in LM Studio or llama.cpp; MLX builds run in LM Studio or mlx-lm.

On the Mac mini M5 Pro (64 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is ~31 tok/s (estimated) at 4-bit; keep the context at or under 256K there, or use a q8 KV cache.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for Nemotron 3.5 Bolt 74B-A9B

Mac mini M5 Pro (48 GB) — smallest current Mac that runs it and cheapest at 15+ tok/s, $2,299 new (Apple list price, checked 2026-11-14), ~31 tok/s (estimated) once the GPU memory limit is raised. Amazon does not stock the Mac mini M5 Pro (48 GB): Apple builds it to order.

FAQ: Nemotron 3.5 Bolt 74B-A9B on a Mac

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

On memory, yes (its Mac runtime carries a 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). Nemotron 3.5 Bolt 74B-A9B needs about 45 GB of unified memory at a short (4K-token) context, so it runs on 25 of the 54 Mac configurations in the LLMCheck index; 21 of them hold it inside macOS’s default GPU memory limit and 4 only after raising that limit. The smallest Mac Apple sells new that runs it is the Mac mini M5 Pro (48 GB).

How much RAM does Nemotron 3.5 Bolt 74B-A9B need?

About 45 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 46 GB in total at 32K and 46 GB at 64K with the default 16-bit cache (about 46 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.

How fast does Nemotron 3.5 Bolt 74B-A9B run on a Mac?

On an M5 Max, the chip the leaderboard quotes it on, the index figure is 64 tok/s (community run) at 5-bit. The best measured figure is 71.7 tok/s on an M5 Max 128 GB (community run, 4-bit). Every Mac’s figure is in the table on this page with its provenance: published, community run or estimated.

What is the cheapest Mac that runs Nemotron 3.5 Bolt 74B-A9B well?

Among Macs Apple sells new, the Mac mini M5 Pro (48 GB), $2,299 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Nemotron 3.5 Bolt 74B-A9B, at ~31 tok/s (estimated), after raising the GPU memory limit.

Do I need to raise the GPU memory limit to run Nemotron 3.5 Bolt 74B-A9B?

On 4 of the 54 configurations, yes: Mac mini M5 Pro 48 GB, Mac Studio M5 Max 48 GB, MacBook Pro M5 Pro 48 GB and 1 more. macOS lets the GPU use only part of unified memory by default (about 37 GB on the Mac mini M5 Pro (48 GB)), and Nemotron 3.5 Bolt 74B-A9B needs about 45 GB. Running sudo sysctl iogpu.wired_limit_mb=43008 in Terminal raises the limit on a 48 GB Mac until the next restart. From 64 GB up, every Mac Apple sells new holds it inside the default limit.

Which quantization of Nemotron 3.5 Bolt 74B-A9B should I use?

Q4_K_M (about 42 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 78 GB) is closer to full quality and needs a 128 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 36 and 25 GB at a quality cost. The index’s reference figure (64 tok/s on an M5 Max) is for its 5-bit build.

How much context can Nemotron 3.5 Bolt 74B-A9B use on a Mac?

Its own window is 256K tokens. At macOS’s default GPU limit, the Mac mini M5 Pro (64 GB) holds about 256K (the full window).

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 ). CC BY 4.0.

How to cite LLMCheck →Data: CC BY 4.0Markdown version

Related

Figures from the LLMCheck index, data version 2026-11-18. Verdicts and context limits are estimates from each model’s catalog memory figure and config.json.