Can I run Nemotron 3.5 Lightning on a Mac?

Yes: Nemotron 3.5 Lightning runs on 43 of the 54 Macs in the LLMCheck index. It needs about 18 GB at a 4K context, 19 GB at 64K. Smallest and cheapest current Mac at 15+ tok/s is the Mac mini M6 24 GB ($1,099; 45 tok/s community-measured), raised GPU limit. Best measured figure: 164.7 tok/s on an M5 Max (community).

RAM at 4K
18
GB
RAM at 64K
19
GB, 16-bit KV
Macs that run it
43
of 54 configs
Best measured
community164.7
tok/s · M5 Max

Nemotron 3.5 Lightning 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 small mixture-of-experts models (40B total or less), the formula’s typical error is about 15% (the median gap to 88 measured plain-decode runs; it tends to undershoot (median −7%), 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 GBRaise GPU limit command ↓Q4_K_Mestimated41 tok/s321K raised—
MacBook Air M5 32 GBRunsQ4_K_Mestimated41 tok/s1M (full)—
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 usedRaise GPU limit command ↓Q4_K_Mestimated34 tok/s321K raised—
MacBook Air M2 24 GB refurbRaise GPU limit command ↓Q4_K_Mestimated29 tok/s321K raised—
MacBook Air M3 24 GB refurbRaise GPU limit command ↓Q4_K_Mestimated29 tok/s321K raised—
MacBook Pro
MacBook Pro M6 16 GBDoesn't fit————
MacBook Pro M5 Pro 24 GBRaise GPU limit command ↓Q4_K_Mcommunity72 tok/s321K raisedM5 Pro page
MacBook Pro M6 24 GBRaise GPU limit command ↓Q4_K_Mcommunity45 tok/s321K raisedM6 page
MacBook Pro M6 32 GBRunsQ4_K_Mcommunity45 tok/s1M (full)M6 page
MacBook Pro M5 Pro 48 GBRunsQ4_K_Mcommunity72 tok/s1M (full)M5 Pro page
MacBook Pro M5 Max 64 GBRunsQ4_0community117 tok/s1M (full)M5 Max page
MacBook Pro M5 Pro 64 GBRunsQ4_K_Mcommunity72 tok/s1M (full)M5 Pro page
MacBook Pro M5 Max 128 GBRunsQ4_0community117 tok/s1M (full)M5 Max page
MacBook Pro M3 Max 64 GB refurbRunsQ4_K_Mestimated85 tok/s1M (full)—
MacBook Pro M3 Max 128 GB refurbRunsQ4_K_Mestimated85 tok/s1M (full)—
Mac mini
Mac mini M6 16 GBDoesn't fit————
Mac mini M5 Pro 24 GBRaise GPU limit command ↓Q4_K_Mcommunity72 tok/s321K raisedM5 Pro page
Mac mini M6 24 GBRaise GPU limit command ↓Q4_K_Mcommunity45 tok/s321K raisedM6 page
Mac mini M6 32 GBRunsQ4_K_Mcommunity45 tok/s1M (full)M6 page
Mac mini M5 Pro 48 GBRunsQ4_K_Mcommunity72 tok/s1M (full)M5 Pro page
Mac mini M5 Pro 64 GBRunsQ4_K_Mcommunity72 tok/s1M (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 usedRaise GPU limit command ↓Q4_K_Mestimated67 tok/s321K raised—
Mac mini M4 24 GB usedRaise GPU limit command ↓Q4_K_Mestimated34 tok/s321K raised—
Mac mini M2 Pro 32 GB refurbRunsQ4_K_Mestimated51 tok/s533K—
Mac mini M4 Pro 48 GB usedRunsQ4_K_Mestimated67 tok/s1M (full)—
Mac mini M4 Pro 64 GB usedRunsQ4_K_Mestimated67 tok/s1M (full)—
iMac
iMac M6 16 GBDoesn't fit————
iMac M6 24 GBRaise GPU limit command ↓Q4_K_Mcommunity45 tok/s321K raisedM6 page
iMac M6 32 GBRunsQ4_K_Mcommunity45 tok/s1M (full)M6 page
Mac Studio
Mac Studio M5 Max 36 GBRunsQ4_K_Mestimated92 tok/s1M (full)M5 Max page
Mac Studio M5 Max 48 GBRunsQ4_0community117 tok/s1M (full)M5 Max page
Mac Studio M5 Max 64 GBRunsQ4_0community117 tok/s1M (full)M5 Max page
Mac Studio M5 Ultra 96 GBRunsQ4_K_Mestimated165 tok/s1M (full)—
Mac Studio M5 Max 128 GBRunsQ4_0community117 tok/s1M (full)M5 Max page
Mac Studio M5 Ultra 256 GBRunsQ4_K_Mestimated165 tok/s1M (full)—
Mac Studio M5 Ultra 512 GBRunsQ4_K_Mestimated165 tok/s1M (full)—
Mac Studio M2 Max 32 GB refurbRunsQ4_K_Mestimated85 tok/s533K—
Mac Studio M1 Ultra 64 GB refurbRunsQ4_K_Mestimated150 tok/s1M (full)—
Mac Studio M4 Max 64 GB usedRunsQ4_K_Mestimated117 tok/s1M (full)—
Mac Studio M2 Max 64 GB refurbRunsQ4_K_Mestimated85 tok/s1M (full)—
Mac Studio M1 Ultra 128 GB refurbRunsQ4_K_Mestimated150 tok/s1M (full)—
Mac Studio M2 Ultra 128 GB refurbRunsQ4_K_Mestimated150 tok/s1M (full)—
Mac Studio M4 Max 128 GB usedRunsQ4_K_Mestimated117 tok/s1M (full)—
Mac Studio M2 Ultra 192 GB refurbRunsQ4_K_Mestimated150 tok/s1M (full)—
Mac Studio M3 Ultra 256 GB usedRunsQ4_K_Mestimated151 tok/s1M (full)—
Mac Studio M3 Ultra 512 GB refurbRunsQ4_K_Mestimated151 tok/s1M (full)—
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 6 of 52 layers; Mamba layers keep a constant state): about 0.4 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 Lightning needs about 18 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 Lightning: memory by quantization

Weights are 30B 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 30B parameters sit in memory although only 3B are read per token. The first row is the catalog’s own figure (about 18 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—18 GB18 GB18 GB32 GB (24 GB with a raised limit)
Q2_K10.2 GB12 GB12 GB13 GB24 GB
Q3_K_M14.7 GB17 GB17 GB17 GB24 GB
Q4_K_M17.1 GB19 GB19 GB19 GB32 GB (24 GB with a raised limit)
Q5_K_M21.3 GB23 GB23 GB24 GB32 GB
Q6_K24.6 GB27 GB27 GB27 GB36 GB (32 GB with a raised limit)
Q8_031.8 GB34 GB34 GB34 GB48 GB
F1660.0 GB62 GB62 GB62 GB96 GB

Measured runs of Nemotron 3.5 Lightning

Every published (filled square) and community (hollow circle) run the index holds for Nemotron 3.5 Lightning: 1 published, 7 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
M5 Max 128 GBMLX4-bitcommunity164.7 tok/s512-token coding answers, median of 5 at T 0.6, thinking off2026-10-18github.com
M5 Max 128 GBMLX4-bitcommunity139.3 tok/s512-token coding answers, median of 5 at T 0.6, thinking off2026-10-18github.com
M5 Max 128 GBllama.cppQ4_0community116.8 tok/s512-token coding answers, median of 5 at T 0.6, thinking off2026-10-18github.com
M5 Max —llama.cppQ4_K_Msourced114 tok/s4K-token input2026-10-13huggingface.co
M5 Pro 48 GBMLX4-bitcommunity93.73 tok/s512-token coding answers, median of 5 at T 0.62026-10-19github.com
M5 Pro 48 GBLM StudioQ4_K_Mcommunity72.3 tok/s512-token coding answers, median of 5 at T 0.62026-10-19github.com
M6 32 GBMLX4-bitcommunity60.3 tok/s1k2026-10-24omlx.ai
M6 32 GBllama.cppQ4_K_Mcommunity45 tok/s—2026-10github.com

Recommended setup

The quickest start is Ollama. Pull the model by its tag (checked on ollama.com, 2026-11-14; the file is about 25 GB):

ollama run nemotron-3.5-lightning:30b

Prefer a window to a terminal? LM Studio downloads the same model with one click. · model card →

On the Mac mini M6 (32 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is 45 tok/s (community run) at Q4_K_M; keep the context at or under 1M there, or use a q8 KV cache. The nemotron-3.5-lightning:30b file fits there.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for Nemotron 3.5 Lightning

Mac mini M6 (24 GB) — smallest current Mac that runs it and cheapest at 15+ tok/s, $1,099 new (Apple list price, checked 2026-11-14), 45 tok/s (community run) once the GPU memory limit is raised. For Ollama: the nemotron-3.5-lightning:30b tag is about 25 GB, so it needs a 36 GB Mac; on 24 GB use a ~5-bit build after raising the GPU limit.

As an Amazon Associate, LLMCheck earns from qualifying purchases. Affiliate links cost you nothing extra and never influence the verdicts.

FAQ: Nemotron 3.5 Lightning on a Mac

Can I run Nemotron 3.5 Lightning on a Mac?

Yes. Nemotron 3.5 Lightning needs about 18 GB of unified memory at a short (4K-token) context, so it runs on 43 of the 54 Mac configurations in the LLMCheck index; 32 of them hold it inside macOS’s default GPU memory limit and 11 only after raising that limit. The smallest Mac Apple sells new that runs it is the Mac mini M6 (24 GB).

How much RAM does Nemotron 3.5 Lightning need?

About 18 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 19 GB in total at 32K and 19 GB at 64K with the default 16-bit cache (about 19 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.

How fast does Nemotron 3.5 Lightning run on a Mac?

On an M5 Max, the chip the leaderboard quotes it on, the index figure is 117 tok/s (community run) at Q4_0. The best measured figure is 164.7 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 Lightning well?

Among Macs Apple sells new, the Mac mini M6 (24 GB), $1,099 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Nemotron 3.5 Lightning, at 45 tok/s (community run), after raising the GPU memory limit.

Do I need to raise the GPU memory limit to run Nemotron 3.5 Lightning?

On 11 of the 54 configurations, yes: iMac M6 24 GB, Mac mini M5 Pro 24 GB, Mac mini M6 24 GB and 8 more. macOS lets the GPU use only part of unified memory by default (about 18 GB on the iMac M6 (24 GB)), and Nemotron 3.5 Lightning needs about 18 GB. Running sudo sysctl iogpu.wired_limit_mb=20480 in Terminal raises the limit on a 24 GB Mac until the next restart. From 32 GB up, every Mac Apple sells new holds it inside the default limit.

Which quantization of Nemotron 3.5 Lightning should I use?

Q4_K_M (about 17 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 32 GB) is closer to full quality and needs a 48 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 15 and 10 GB at a quality cost. The index’s reference figure (117 tok/s on an M5 Max) is for its Q4_0 build.

How much context can Nemotron 3.5 Lightning use on a Mac?

Its own window is 1M tokens. At macOS’s default GPU limit, the Mac mini M6 (32 GB) holds about 1M (the full window).

Cite this page

LLMCheck. (2026). Can I run Nemotron 3.5 Lightning on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/nemotron-35-lightning/ (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.