Can I run Ministral 3 14B on a Mac?

Yes: Ministral 3 14B runs on 53 of the 54 Macs in the LLMCheck index. It needs about 10 GB of unified memory at a 4K context and about 21 GB at 64K. The smallest and cheapest current Mac that runs it at 15+ tok/s is the Mac mini M6 16 GB ($899; ~15 tok/s est.). No measured run yet.

RAM at 4K
10
GB
RAM at 64K
21
GB, 16-bit KV
Macs that run it
53
of 54 configs
Best measured
—
no measured run

Ministral 3 14B 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)Doesn't fit needs more memory than the Mac has
MacVerdictBuildSpeedMax contextModel page
MacBook Air
MacBook Air M5 16 GBRunsQ4_K_Mestimated15 tok/s14K—
MacBook Air M5 24 GBRunsQ4_K_Mestimated15 tok/s50K—
MacBook Air M5 32 GBRunsQ4_K_Mestimated15 tok/s93K—
MacBook Air M1 8 GB refurbDoesn't fit————
MacBook Air M4 16 GB usedRuns, slowlyQ4_K_Mestimated12 tok/s7K—
MacBook Air M2 16 GB refurbRuns, slowlyQ4_K_Mestimated10 tok/s7K—
MacBook Air M3 16 GB refurbRuns, slowlyQ4_K_Mestimated10 tok/s7K—
MacBook Air M1 16 GB refurbRuns, slowlyQ4_K_Mestimated7 tok/s7K—
MacBook Air M4 24 GB usedRuns, slowlyQ4_K_Mestimated12 tok/s39K—
MacBook Air M2 24 GB refurbRuns, slowlyQ4_K_Mestimated10 tok/s39K—
MacBook Air M3 24 GB refurbRuns, slowlyQ4_K_Mestimated10 tok/s39K—
MacBook Pro
MacBook Pro M6 16 GBRunsQ4_K_Mestimated15 tok/s14K—
MacBook Pro M5 Pro 24 GBRunsQ4_K_Mestimated29 tok/s50K—
MacBook Pro M6 24 GBRunsQ4_K_Mestimated17 tok/s50K—
MacBook Pro M6 32 GBRunsQ4_K_Mestimated17 tok/s93K—
MacBook Pro M5 Pro 48 GBRunsQ4_K_Mestimated29 tok/s167K—
MacBook Pro M5 Max 64 GBRunsQ4_K_Mestimated55 tok/s253K—
MacBook Pro M5 Pro 64 GBRunsQ4_K_Mestimated29 tok/s253K—
MacBook Pro M5 Max 128 GBRunsQ4_K_Mestimated55 tok/s256K (full)—
MacBook Pro M3 Max 64 GB refurbRunsQ4_K_Mestimated37 tok/s230K—
MacBook Pro M3 Max 128 GB refurbRunsQ4_K_Mestimated37 tok/s256K (full)—
Mac mini
Mac mini M6 16 GBRunsQ4_K_Mestimated15 tok/s14K—
Mac mini M5 Pro 24 GBRunsQ4_K_Mestimated29 tok/s50K—
Mac mini M6 24 GBRunsQ4_K_Mestimated17 tok/s50K—
Mac mini M6 32 GBRunsQ4_K_Mestimated17 tok/s93K—
Mac mini M5 Pro 48 GBRunsQ4_K_Mestimated29 tok/s167K—
Mac mini M5 Pro 64 GBRunsQ4_K_Mestimated29 tok/s253K—
Mac mini M2 Pro 16 GB refurbRunsQ4_K_Mestimated19 tok/s7K—
Mac mini M4 16 GB usedRuns, slowlyQ4_K_Mestimated12 tok/s7K—
Mac mini M4 Pro 24 GB usedRunsQ4_K_Mestimated26 tok/s39K—
Mac mini M4 24 GB usedRuns, slowlyQ4_K_Mestimated12 tok/s39K—
Mac mini M2 Pro 32 GB refurbRunsQ4_K_Mestimated19 tok/s71K—
Mac mini M4 Pro 48 GB usedRunsQ4_K_Mestimated26 tok/s158K—
Mac mini M4 Pro 64 GB usedRunsQ4_K_Mestimated26 tok/s230K—
iMac
iMac M6 16 GBRunsQ4_K_Mestimated15 tok/s14K—
iMac M6 24 GBRunsQ4_K_Mestimated17 tok/s50K—
iMac M6 32 GBRunsQ4_K_Mestimated17 tok/s93K—
Mac Studio
Mac Studio M5 Max 36 GBRunsQ4_K_Mestimated42 tok/s111K—
Mac Studio M5 Max 48 GBRunsQ4_K_Mestimated55 tok/s167K—
Mac Studio M5 Max 64 GBRunsQ4_K_Mestimated55 tok/s253K—
Mac Studio M5 Ultra 96 GBRunsQ4_K_Mestimated102 tok/s256K (full)—
Mac Studio M5 Max 128 GBRunsQ4_K_Mestimated55 tok/s256K (full)—
Mac Studio M5 Ultra 256 GBRunsQ4_K_Mestimated102 tok/s256K (full)—
Mac Studio M5 Ultra 512 GBRunsQ4_K_Mestimated102 tok/s256K (full)—
Mac Studio M2 Max 32 GB refurbRunsQ4_K_Mestimated37 tok/s71K—
Mac Studio M1 Ultra 64 GB refurbRunsQ4_K_Mestimated70 tok/s230K—
Mac Studio M4 Max 64 GB usedRunsQ4_K_Mestimated49 tok/s230K—
Mac Studio M2 Max 64 GB refurbRunsQ4_K_Mestimated37 tok/s230K—
Mac Studio M1 Ultra 128 GB refurbRunsQ4_K_Mestimated70 tok/s256K (full)—
Mac Studio M2 Ultra 128 GB refurbRunsQ4_K_Mestimated70 tok/s256K (full)—
Mac Studio M4 Max 128 GB usedRunsQ4_K_Mestimated49 tok/s256K (full)—
Mac Studio M2 Ultra 192 GB refurbRunsQ4_K_Mestimated70 tok/s256K (full)—
Mac Studio M3 Ultra 256 GB usedRunsQ4_K_Mestimated71 tok/s256K (full)—
Mac Studio M3 Ultra 512 GB refurbRunsQ4_K_Mestimated71 tok/s256K (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 (GQA on all 40 layers (8 kv heads x 128)): about 10.7 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.

macOS’s GPU memory limit

macOS lets the GPU use only part of unified memory by default. Ministral 3 14B fits inside that default limit on every Mac it fits at all, so no Mac in the table needs it raised at a short context. Long contexts may still need it: the context column already uses each Mac’s default limit.

Ministral 3 14B: memory by quantization

Weights are 14B 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 10 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—10 GB15 GB20 GB16 GB
Q2_K4.8 GB7 GB11 GB17 GB16 GB
Q3_K_M6.9 GB9 GB14 GB19 GB16 GB
Q4_K_M8.0 GB10 GB15 GB20 GB16 GB
Q5_K_M9.9 GB12 GB17 GB22 GB24 GB (16 GB with a raised limit)
Q6_K11.5 GB13 GB18 GB24 GB24 GB
Q8_014.8 GB17 GB22 GB27 GB24 GB
F1628.0 GB30 GB35 GB40 GB48 GB (36 GB with a raised limit)

Measured runs

The index holds no published or community run of Ministral 3 14B yet, so every speed on this page is an estimate from the memory-bandwidth model. LLMCheck runs no tests of its own: if you have run it on a Mac, submit the figure with its setup →

Recommended setup

The quickest start is Ollama. Pull the model by its tag (checked on ollama.com, 2026-11-14; the file is about 9.1 GB):

ollama run ministral-3:14b

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 ~15 tok/s (estimated) at Q4_K_M; keep the context at or under 14K there, or use a q8 KV cache. The ministral-3:14b file fits there.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for Ministral 3 14B

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), ~15 tok/s (estimated).

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

FAQ: Ministral 3 14B on a Mac

Can I run Ministral 3 14B on a Mac?

Yes. Ministral 3 14B needs about 10 GB of unified memory at a short (4K-token) context, so it runs on 53 of the 54 Mac configurations in the LLMCheck index. The smallest Mac Apple sells new that runs it is the Mac mini M6 (16 GB).

How much RAM does Ministral 3 14B need?

About 10 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 15 GB in total at 32K and 21 GB at 64K with the default 16-bit cache (about 16 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.

How fast does Ministral 3 14B run on a Mac?

On an M5 Max, the chip the leaderboard quotes it on, the index figure is ~55 tok/s (estimated) at Q4_K_M. No published or community run is in the index yet; every speed is an estimate from the memory-bandwidth model. 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 Ministral 3 14B 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 Ministral 3 14B, at ~15 tok/s (estimated).

Do I need to raise the GPU memory limit to run Ministral 3 14B?

No. On all 53 Mac configurations where Ministral 3 14B fits, it fits inside that Mac’s default GPU memory limit at a short context; only a long context on the smallest of them can push it over.

Which quantization of Ministral 3 14B should I use?

Q4_K_M (about 8 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 15 GB) is closer to full quality and needs a 24 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 7 and 5 GB at a quality cost. The index’s reference figure (55 tok/s on an M5 Max) is for its Q4_K_M build.

How much context can Ministral 3 14B use on a Mac?

Its own window is 256K tokens. At macOS’s default GPU limit, the Mac mini M6 (16 GB) holds about 14K. The full window needs about 53 GB, which a 96 GB Mac holds at the default limit. A q8 KV cache roughly doubles these lengths.

Cite this page

LLMCheck. (2026). Can I run Ministral 3 14B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/ministral-3-14b/ (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.