Can I run Apertus 1.5 8B on a Mac?

Yes: Apertus 1.5 8B runs on all 54 Macs in the LLMCheck index. It needs about 5 GB at a 4K context. The smallest and cheapest current Mac that runs it at 15+ tok/s is the Mac mini M6 16 GB ($899; ~25 tok/s est.). No measured run is in the index yet, so every speed here is an estimate.

RAM at 4K
5
GB
RAM at 64K
—
no KV figure
Macs that run it
54
of 54 configs
Best measured
—
no measured run

Apertus 1.5 8B 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_Mestimated25 tok/s——
MacBook Air M5 24 GBRunsQ4_K_Mestimated25 tok/s——
MacBook Air M5 32 GBRunsQ4_K_Mestimated25 tok/s——
MacBook Air M1 8 GB refurbRuns, slowlyQ4_K_Mestimated11 tok/s——
MacBook Air M4 16 GB usedRunsQ4_K_Mestimated20 tok/s——
MacBook Air M2 16 GB refurbRunsQ4_K_Mestimated17 tok/s——
MacBook Air M3 16 GB refurbRunsQ4_K_Mestimated17 tok/s——
MacBook Air M1 16 GB refurbRuns, slowlyQ4_K_Mestimated11 tok/s——
MacBook Air M4 24 GB usedRunsQ4_K_Mestimated20 tok/s——
MacBook Air M2 24 GB refurbRunsQ4_K_Mestimated17 tok/s——
MacBook Air M3 24 GB refurbRunsQ4_K_Mestimated17 tok/s——
MacBook Pro
MacBook Pro M6 16 GBRunsQ4_K_Mestimated25 tok/s——
MacBook Pro M5 Pro 24 GBRunsQ4_K_Mestimated49 tok/s——
MacBook Pro M6 24 GBRunsQ4_K_Mestimated28 tok/s——
MacBook Pro M6 32 GBRunsQ4_K_Mestimated28 tok/s——
MacBook Pro M5 Pro 48 GBRunsQ4_K_Mestimated49 tok/s——
MacBook Pro M5 Max 64 GBRunsQ4_K_Mestimated91 tok/s——
MacBook Pro M5 Pro 64 GBRunsQ4_K_Mestimated49 tok/s——
MacBook Pro M5 Max 128 GBRunsQ4_K_Mestimated91 tok/s——
MacBook Pro M3 Max 64 GB refurbRunsQ4_K_Mestimated62 tok/s——
MacBook Pro M3 Max 128 GB refurbRunsQ4_K_Mestimated62 tok/s——
Mac mini
Mac mini M6 16 GBRunsQ4_K_Mestimated25 tok/s——
Mac mini M5 Pro 24 GBRunsQ4_K_Mestimated49 tok/s——
Mac mini M6 24 GBRunsQ4_K_Mestimated28 tok/s——
Mac mini M6 32 GBRunsQ4_K_Mestimated28 tok/s——
Mac mini M5 Pro 48 GBRunsQ4_K_Mestimated49 tok/s——
Mac mini M5 Pro 64 GBRunsQ4_K_Mestimated49 tok/s——
Mac mini M2 Pro 16 GB refurbRunsQ4_K_Mestimated33 tok/s——
Mac mini M4 16 GB usedRunsQ4_K_Mestimated20 tok/s——
Mac mini M4 Pro 24 GB usedRunsQ4_K_Mestimated44 tok/s——
Mac mini M4 24 GB usedRunsQ4_K_Mestimated20 tok/s——
Mac mini M2 Pro 32 GB refurbRunsQ4_K_Mestimated33 tok/s——
Mac mini M4 Pro 48 GB usedRunsQ4_K_Mestimated44 tok/s——
Mac mini M4 Pro 64 GB usedRunsQ4_K_Mestimated44 tok/s——
iMac
iMac M6 16 GBRunsQ4_K_Mestimated25 tok/s——
iMac M6 24 GBRunsQ4_K_Mestimated28 tok/s——
iMac M6 32 GBRunsQ4_K_Mestimated28 tok/s——
Mac Studio
Mac Studio M5 Max 36 GBRunsQ4_K_Mestimated71 tok/s——
Mac Studio M5 Max 48 GBRunsQ4_K_Mestimated91 tok/s——
Mac Studio M5 Max 64 GBRunsQ4_K_Mestimated91 tok/s——
Mac Studio M5 Ultra 96 GBRunsQ4_K_Mestimated161 tok/s——
Mac Studio M5 Max 128 GBRunsQ4_K_Mestimated91 tok/s——
Mac Studio M5 Ultra 256 GBRunsQ4_K_Mestimated161 tok/s——
Mac Studio M5 Ultra 512 GBRunsQ4_K_Mestimated161 tok/s——
Mac Studio M2 Max 32 GB refurbRunsQ4_K_Mestimated62 tok/s——
Mac Studio M1 Ultra 64 GB refurbRunsQ4_K_Mestimated114 tok/s——
Mac Studio M4 Max 64 GB usedRunsQ4_K_Mestimated82 tok/s——
Mac Studio M2 Max 64 GB refurbRunsQ4_K_Mestimated62 tok/s——
Mac Studio M1 Ultra 128 GB refurbRunsQ4_K_Mestimated114 tok/s——
Mac Studio M2 Ultra 128 GB refurbRunsQ4_K_Mestimated114 tok/s——
Mac Studio M4 Max 128 GB usedRunsQ4_K_Mestimated82 tok/s——
Mac Studio M2 Ultra 192 GB refurbRunsQ4_K_Mestimated114 tok/s——
Mac Studio M3 Ultra 256 GB usedRunsQ4_K_Mestimated116 tok/s——
Mac Studio M3 Ultra 512 GB refurbRunsQ4_K_Mestimated116 tok/s——
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

The index has no KV-cache figure for Apertus 1.5 8B yet, so the context column shows —: its minimum RAM covers a short (about 4K-token) prompt only.

macOS’s GPU memory limit

macOS lets the GPU use only part of unified memory by default. Apertus 1.5 8B 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.

Apertus 1.5 8B: memory by quantization

Weights are 8B 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 5 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—5 GB——16 GB
Q2_K2.7 GB5 GB——16 GB
Q3_K_M3.9 GB6 GB——16 GB
Q4_K_M4.6 GB7 GB——16 GB
Q5_K_M5.7 GB8 GB——16 GB
Q6_K6.6 GB9 GB——16 GB
Q8_08.5 GB10 GB——16 GB
F1616.0 GB18 GB——32 GB (24 GB with a raised limit)

Measured runs

The index holds no published or community run of Apertus 1.5 8B 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 index has no verified Ollama tag for Apertus 1.5 8B. Start from its listing and copy the exact name of a build that fits: Search the Ollama library → · model card →

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

On the Mac mini M6 (16 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is ~25 tok/s (estimated) at Q4_K_M; keep the context at or under a short prompt there, or use a q8 KV cache.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for Apertus 1.5 8B

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), ~25 tok/s (estimated).

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

FAQ: Apertus 1.5 8B on a Mac

Can I run Apertus 1.5 8B on a Mac?

Yes. Apertus 1.5 8B needs about 5 GB of unified memory at a short (4K-token) context, so it runs on 54 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 Apertus 1.5 8B need?

About 5 GB at a short (about 4K-token) context: the weights plus about 2 GB for the runtime. The index has no KV-cache figure for Apertus 1.5 8B yet, so it cannot say how much a long context adds.

How fast does Apertus 1.5 8B run on a Mac?

On an M5 Max, the chip the leaderboard quotes it on, the index figure is ~91 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 Apertus 1.5 8B 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 Apertus 1.5 8B, at ~25 tok/s (estimated).

Do I need to raise the GPU memory limit to run Apertus 1.5 8B?

No. On all 54 Mac configurations where Apertus 1.5 8B 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 Apertus 1.5 8B should I use?

Q4_K_M (about 5 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 8 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 4 and 3 GB at a quality cost. The index’s reference figure (91 tok/s on an M5 Max) is for its Q4_K_M build.

Cite this page

LLMCheck. (2026). Can I run Apertus 1.5 8B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/apertus-15-8b/ (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.