Can I run Nemotron 3.5 Bolt E4B on a Mac?

Yes: Nemotron 3.5 Bolt E4B runs on 53 of 54 Macs in the LLMCheck index. It needs about 6 GB at a 4K context, 8 GB at 64K. The smallest and cheapest current Mac that runs it at 15+ tok/s is the Mac mini M6 16 GB ($899; ~42 tok/s est.). Best measured: 46.4 tok/s on an M5 Pro (community).

RAM at 4K
6
GB
RAM at 64K
8
GB, 16-bit KV
Macs that run it
53
of 54 configs
Best measured
community46.4
tok/s · M5 Pro

Nemotron 3.5 Bolt E4B 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 dense models, the formula’s typical error is about 9% (the median gap to 75 measured plain-decode runs; it tends to undershoot (median −6%), 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)Over GPU limit fits RAM on paper, but even a safe raise is shortDoesn't fit needs more memory than the Mac has
MacVerdictBuildSpeedMax contextModel page
MacBook Air
MacBook Air M5 16 GBRunsQ4_K_Mestimated42 tok/s64K (full)—
MacBook Air M5 24 GBRunsQ4_K_Mestimated42 tok/s64K (full)—
MacBook Air M5 32 GBRunsQ4_K_Mestimated42 tok/s64K (full)—
MacBook Air M1 8 GB refurbOver GPU limit why ↓Q4_K_Mestimated19 tok/s——
MacBook Air M4 16 GB usedRunsQ4_K_Mestimated33 tok/s64K (full)M4 page
MacBook Air M2 16 GB refurbRunsQ4_K_Mestimated28 tok/s64K (full)—
MacBook Air M3 16 GB refurbRunsQ4_K_Mestimated28 tok/s64K (full)—
MacBook Air M1 16 GB refurbRunsQ4_K_Mestimated19 tok/s64K (full)—
MacBook Air M4 24 GB usedRunsQ4_K_Mestimated33 tok/s64K (full)M4 page
MacBook Air M2 24 GB refurbRunsQ4_K_Mestimated28 tok/s64K (full)—
MacBook Air M3 24 GB refurbRunsQ4_K_Mestimated28 tok/s64K (full)—
MacBook Pro
MacBook Pro M6 16 GBRunsQ4_K_Mestimated42 tok/s64K (full)—
MacBook Pro M5 Pro 24 GBRunsQ4_K_Mestimated79 tok/s64K (full)M5 Pro page
MacBook Pro M6 24 GBRunsQ4_K_Mestimated46 tok/s64K (full)—
MacBook Pro M6 32 GBRunsQ4_K_Mestimated46 tok/s64K (full)—
MacBook Pro M5 Pro 48 GBRunsQ4_K_Mestimated79 tok/s64K (full)M5 Pro page
MacBook Pro M5 Max 64 GBRunsQ4_K_Mestimated161 tok/s64K (full)M5 Max page
MacBook Pro M5 Pro 64 GBRunsQ4_K_Mestimated79 tok/s64K (full)M5 Pro page
MacBook Pro M5 Max 128 GBRunsQ4_K_Mestimated161 tok/s64K (full)M5 Max page
MacBook Pro M3 Max 64 GB refurbRunsQ4_K_Mestimated100 tok/s64K (full)M3 Max page
MacBook Pro M3 Max 128 GB refurbRunsQ4_K_Mestimated100 tok/s64K (full)M3 Max page
Mac mini
Mac mini M6 16 GBRunsQ4_K_Mestimated42 tok/s64K (full)—
Mac mini M5 Pro 24 GBRunsQ4_K_Mestimated79 tok/s64K (full)M5 Pro page
Mac mini M6 24 GBRunsQ4_K_Mestimated46 tok/s64K (full)—
Mac mini M6 32 GBRunsQ4_K_Mestimated46 tok/s64K (full)—
Mac mini M5 Pro 48 GBRunsQ4_K_Mestimated79 tok/s64K (full)M5 Pro page
Mac mini M5 Pro 64 GBRunsQ4_K_Mestimated79 tok/s64K (full)M5 Pro page
Mac mini M2 Pro 16 GB refurbRunsQ4_K_Mestimated54 tok/s64K (full)—
Mac mini M4 16 GB usedRunsQ4_K_Mestimated33 tok/s64K (full)M4 page
Mac mini M4 Pro 24 GB usedRunsQ4_K_Mestimated72 tok/s64K (full)—
Mac mini M4 24 GB usedRunsQ4_K_Mestimated33 tok/s64K (full)M4 page
Mac mini M2 Pro 32 GB refurbRunsQ4_K_Mestimated54 tok/s64K (full)—
Mac mini M4 Pro 48 GB usedRunsQ4_K_Mestimated72 tok/s64K (full)—
Mac mini M4 Pro 64 GB usedRunsQ4_K_Mestimated72 tok/s64K (full)—
iMac
iMac M6 16 GBRunsQ4_K_Mestimated42 tok/s64K (full)—
iMac M6 24 GBRunsQ4_K_Mestimated46 tok/s64K (full)—
iMac M6 32 GBRunsQ4_K_Mestimated46 tok/s64K (full)—
Mac Studio
Mac Studio M5 Max 36 GBRunsQ4_K_Mestimated113 tok/s64K (full)M5 Max page
Mac Studio M5 Max 48 GBRunsQ4_K_Mestimated161 tok/s64K (full)M5 Max page
Mac Studio M5 Max 64 GBRunsQ4_K_Mestimated161 tok/s64K (full)M5 Max page
Mac Studio M5 Ultra 96 GBRunsQ4_K_Mestimated261 tok/s64K (full)—
Mac Studio M5 Max 128 GBRunsQ4_K_Mestimated161 tok/s64K (full)M5 Max page
Mac Studio M5 Ultra 256 GBRunsQ4_K_Mestimated261 tok/s64K (full)—
Mac Studio M5 Ultra 512 GBRunsQ4_K_Mestimated261 tok/s64K (full)—
Mac Studio M2 Max 32 GB refurbRunsQ4_K_Mestimated100 tok/s64K (full)—
Mac Studio M1 Ultra 64 GB refurbRunsQ4_K_Mestimated196 tok/s64K (full)—
Mac Studio M4 Max 64 GB usedRunsQ4_K_Mestimated147 tok/s64K (full)—
Mac Studio M2 Max 64 GB refurbRunsQ4_K_Mestimated100 tok/s64K (full)—
Mac Studio M1 Ultra 128 GB refurbRunsQ4_K_Mestimated196 tok/s64K (full)—
Mac Studio M2 Ultra 128 GB refurbRunsQ4_K_Mestimated196 tok/s64K (full)—
Mac Studio M4 Max 128 GB usedRunsQ4_K_Mestimated147 tok/s64K (full)—
Mac Studio M2 Ultra 192 GB refurbRunsQ4_K_Mestimated196 tok/s64K (full)—
Mac Studio M3 Ultra 256 GB usedRunsQ4_K_Mestimated199 tok/s64K (full)—
Mac Studio M3 Ultra 512 GB refurbRunsQ4_K_Mestimated199 tok/s64K (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 (config.json of nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16, the base checkpoint the 4GB quant names (that repo has none). 4 full layers (2 kv heads x 512) + 20 sliding layers (2 x 256, window 512); the last 18 layers share earlier layers' KV and store none): about 1.1 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 E4B needs about 6 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. On the Macs marked Over GPU limit even that raise falls short: the model fits the Mac’s RAM on paper, but a smaller quant or a bigger Mac is the realistic route.

Nemotron 3.5 Bolt E4B: memory by quantization

Weights are 4B 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. The first row is the catalog’s own figure (about 6 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—6 GB6 GB7 GB16 GB
Q2_K1.4 GB3 GB4 GB4 GB16 GB
Q3_K_M2.0 GB4 GB4 GB5 GB16 GB
Q4_K_M2.3 GB4 GB5 GB5 GB16 GB
Q5_K_M2.8 GB5 GB5 GB6 GB16 GB
Q6_K3.3 GB5 GB6 GB6 GB16 GB
Q8_04.2 GB6 GB7 GB7 GB16 GB
F168.0 GB10 GB10 GB11 GB16 GB

Measured runs of Nemotron 3.5 Bolt E4B

Every published (filled square) and community (hollow circle) run the index holds for Nemotron 3.5 Bolt E4B: 0 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
M3 Max 36 GBMLX4-bitcommunity72.98 tok/sshort chat prompt, 256 generated, greedy2026-10-23huggingface.co binned
M3 Max 36 GBMLX6-bitcommunity55.22 tok/sshort chat prompt, 256 generated, greedy2026-10-23huggingface.co binned
M3 Max 36 GBMLX8-bitcommunity45.26 tok/sshort chat prompt, 256 generated, greedy2026-10-23huggingface.co binned
M3 Max 36 GBMLXBF16community26.53 tok/sshort chat prompt, 256 generated, greedy2026-10-23huggingface.co binned
M5 Pro 64 GBMLXoQ8ecommunity46.4 tok/s1k2026-10-23omlx.ai
M4 24 GBMLXOptiQ mixed 4/8-bitcommunity26.6 tok/scode prompt, batch 1, greedy, thinking off, best of 32026-10-24huggingface.co
M4 16 GBllama.cppQ4_K_Mcommunity26.6 tok/sshort Japanese prompt, ~400 characters generated, -c 81922026-10-24note.com not an anchor

Recommended setup

The quickest start is Ollama. Pull the model by its tag (checked on ollama.com, 2026-11-14; the file is about 7.9 GB):

ollama run nemotron-3.5-bolt:e4b

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

On the Mac mini M6 (16 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is ~42 tok/s (estimated) at Q4_K_M; keep the context at or under 64K there, or use a q8 KV cache. The nemotron-3.5-bolt:e4b file fits there.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for Nemotron 3.5 Bolt E4B

Mac mini M6 (16 GB) — smallest current Mac that runs it and cheapest at 15+ tok/s, $899 new (Apple list price, checked 2026-11-14), ~42 tok/s (estimated).

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

FAQ: Nemotron 3.5 Bolt E4B on a Mac

Can I run Nemotron 3.5 Bolt E4B on a Mac?

Yes. Nemotron 3.5 Bolt E4B needs about 6 GB of unified memory at a short (4K-token) context, so it runs on 53 of the 54 Mac configurations in the LLMCheck index. On 1 more it fits the RAM, but not even a safely raised GPU limit. The smallest Mac Apple sells new that runs it is the Mac mini M6 (16 GB).

How much RAM does Nemotron 3.5 Bolt E4B need?

About 6 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 7 GB in total at 32K and 8 GB at 64K with the default 16-bit cache (about 7 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 E4B run on a Mac?

On an M5 Max, the chip the leaderboard quotes it on, the index figure is ~161 tok/s (estimated) at Q4_K_M. The best measured figure is 46.4 tok/s on an M5 Pro 64 GB (community run, oQ8e). 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 E4B well?

Among Macs Apple sells new, the Mac mini M6 (16 GB), $899 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Nemotron 3.5 Bolt E4B, at ~42 tok/s (estimated).

Do I need to raise the GPU memory limit to run Nemotron 3.5 Bolt E4B?

On MacBook Air M1 8 GB (used) even a safely raised limit is short: expect heavy swapping, a CPU split or an out-of-memory error. From 16 GB up, every Mac Apple sells new holds it inside the default limit.

Which quantization of Nemotron 3.5 Bolt E4B should I use?

Q4_K_M (about 2 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 4 GB) is closer to full quality and needs a 16 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 2 and 1 GB at a quality cost. The index’s reference figure (161 tok/s on an M5 Max) is for its Q4_K_M build.

How much context can Nemotron 3.5 Bolt E4B use on a Mac?

Its own window is 64K tokens. At macOS’s default GPU limit, the Mac mini M6 (16 GB) holds about 64K (the full window).

Cite this page

LLMCheck. (2026). Can I run Nemotron 3.5 Bolt E4B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/nemotron-35-bolt-e4b/ (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.