Can I run DeepSeek R1 32B on a Mac?

Yes: DeepSeek R1 32B runs on 32 of 54 Macs in the LLMCheck index. It needs about 22 GB of unified memory at a 4K context and about 39 GB at 64K. Smallest current Mac: the Mac mini M6 32 GB; cheapest at 15+ tok/s: the Mac Studio M5 Max 36 GB ($2,499; ~19 tok/s est.). No measured run yet.

RAM at 4K
22
GB
RAM at 64K
39
GB, 16-bit KV
Macs that run it
32
of 54 configs
Best measured
—
no measured run

DeepSeek R1 32B 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 GBDoesn't fit————
MacBook Air M5 24 GBOver GPU limit why ↓Q4_K_Mestimated7 tok/s——
MacBook Air M5 32 GBRuns, slowlyQ4_K_Mestimated7 tok/s15K—
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 usedOver GPU limit why ↓Q4_K_Mestimated5 tok/s——
MacBook Air M2 24 GB refurbOver GPU limit why ↓Q4_K_Mestimated4 tok/s——
MacBook Air M3 24 GB refurbOver GPU limit why ↓Q4_K_Mestimated4 tok/s——
MacBook Pro
MacBook Pro M6 16 GBDoesn't fit————
MacBook Pro M5 Pro 24 GBOver GPU limit why ↓Q4_K_Mestimated13 tok/s——
MacBook Pro M6 24 GBOver GPU limit why ↓Q4_K_Mestimated7 tok/s——
MacBook Pro M6 32 GBRuns, slowlyQ4_K_Mestimated7 tok/s15K—
MacBook Pro M5 Pro 48 GBRuns, slowlyQ4_K_Mestimated13 tok/s61K—
MacBook Pro M5 Max 64 GBRunsQ4_K_Mestimated25 tok/s115K—
MacBook Pro M5 Pro 64 GBRuns, slowlyQ4_K_Mestimated13 tok/s115K—
MacBook Pro M5 Max 128 GBRunsQ4_K_Mestimated25 tok/s128K (full)—
MacBook Pro M3 Max 64 GB refurbRunsQ4_K_Mestimated17 tok/s100K—
MacBook Pro M3 Max 128 GB refurbRunsQ4_K_Mestimated17 tok/s128K (full)—
Mac mini
Mac mini M6 16 GBDoesn't fit————
Mac mini M5 Pro 24 GBOver GPU limit why ↓Q4_K_Mestimated13 tok/s——
Mac mini M6 24 GBOver GPU limit why ↓Q4_K_Mestimated7 tok/s——
Mac mini M6 32 GBRuns, slowlyQ4_K_Mestimated7 tok/s15K—
Mac mini M5 Pro 48 GBRuns, slowlyQ4_K_Mestimated13 tok/s61K—
Mac mini M5 Pro 64 GBRuns, slowlyQ4_K_Mestimated13 tok/s115K—
Mac mini M2 Pro 16 GB refurbDoesn't fit————
Mac mini M4 16 GB usedDoesn't fit————
Mac mini M4 Pro 24 GB usedOver GPU limit why ↓Q4_K_Mestimated12 tok/s——
Mac mini M4 24 GB usedOver GPU limit why ↓Q4_K_Mestimated5 tok/s——
Mac mini M2 Pro 32 GB refurbRaise GPU limit (macOS 15) command ↓Q4_K_Mestimated9 tok/s26K raised—
Mac mini M4 Pro 48 GB usedRuns, slowlyQ4_K_Mestimated12 tok/s56K—
Mac mini M4 Pro 64 GB usedRuns, slowlyQ4_K_Mestimated12 tok/s100K—
iMac
iMac M6 16 GBDoesn't fit————
iMac M6 24 GBOver GPU limit why ↓Q4_K_Mestimated7 tok/s——
iMac M6 32 GBRuns, slowlyQ4_K_Mestimated7 tok/s15K—
Mac Studio
Mac Studio M5 Max 36 GBRunsQ4_K_Mestimated19 tok/s26K—
Mac Studio M5 Max 48 GBRunsQ4_K_Mestimated25 tok/s61K—
Mac Studio M5 Max 64 GBRunsQ4_K_Mestimated25 tok/s115K—
Mac Studio M5 Ultra 96 GBRunsQ4_K_Mestimated48 tok/s128K (full)—
Mac Studio M5 Max 128 GBRunsQ4_K_Mestimated25 tok/s128K (full)—
Mac Studio M5 Ultra 256 GBRunsQ4_K_Mestimated48 tok/s128K (full)—
Mac Studio M5 Ultra 512 GBRunsQ4_K_Mestimated48 tok/s128K (full)—
Mac Studio M2 Max 32 GB refurbRaise GPU limit (macOS 15) command ↓Q4_K_Mestimated17 tok/s26K raised—
Mac Studio M1 Ultra 64 GB refurbRunsQ4_K_Mestimated32 tok/s100K—
Mac Studio M4 Max 64 GB usedRunsQ4_K_Mestimated23 tok/s100K—
Mac Studio M2 Max 64 GB refurbRunsQ4_K_Mestimated17 tok/s100K—
Mac Studio M1 Ultra 128 GB refurbRunsQ4_K_Mestimated32 tok/s128K (full)—
Mac Studio M2 Ultra 128 GB refurbRunsQ4_K_Mestimated32 tok/s128K (full)—
Mac Studio M4 Max 128 GB usedRunsQ4_K_Mestimated23 tok/s128K (full)—
Mac Studio M2 Ultra 192 GB refurbRunsQ4_K_Mestimated32 tok/s128K (full)—
Mac Studio M3 Ultra 256 GB usedRunsQ4_K_Mestimated33 tok/s128K (full)—
Mac Studio M3 Ultra 512 GB refurbRunsQ4_K_Mestimated33 tok/s128K (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 64 layers (8 kv heads x 128)): about 17.2 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 DeepSeek R1 32B needs about 22 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.

DeepSeek R1 32B: memory by quantization

Weights are 32B 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 22 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—22 GB30 GB38 GB32 GB
Q2_K10.9 GB13 GB20 GB29 GB24 GB
Q3_K_M15.7 GB18 GB25 GB34 GB24 GB
Q4_K_M18.2 GB20 GB28 GB36 GB32 GB
Q5_K_M22.7 GB25 GB32 GB41 GB32 GB
Q6_K26.2 GB28 GB36 GB44 GB48 GB (36 GB with a raised limit)
Q8_033.9 GB36 GB43 GB52 GB48 GB
F1664.0 GB66 GB74 GB82 GB96 GB

Measured runs

The index holds no published or community run of DeepSeek R1 32B 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 20 GB):

ollama run deepseek-r1:32b

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 ~7 tok/s (estimated) at Q4_K_M; keep the context at or under 15K there, or use a q8 KV cache. The deepseek-r1:32b file fits there.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for DeepSeek R1 32B

Mac mini M6 (32 GB) — smallest current Mac that runs it, $1,299 new (Apple list price, checked 2026-11-14), ~7 tok/s (estimated). Mac Studio M5 Max (36 GB) — cheapest at 15+ tok/s, $2,499 new (Apple list price, checked 2026-11-14), ~19 tok/s (estimated). Amazon does not stock the Mac mini M6 (32 GB): Apple builds it to order.

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

FAQ: DeepSeek R1 32B on a Mac

Can I run DeepSeek R1 32B on a Mac?

Yes. DeepSeek R1 32B needs about 22 GB of unified memory at a short (4K-token) context, so it runs on 32 of the 54 Mac configurations in the LLMCheck index; 30 of them hold it inside macOS’s default GPU memory limit and 2 only after raising that limit. On 11 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 (32 GB).

How much RAM does DeepSeek R1 32B need?

About 22 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 30 GB in total at 32K and 39 GB at 64K with the default 16-bit cache (about 31 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.

How fast does DeepSeek R1 32B run on a Mac?

On an M5 Max, the chip the leaderboard quotes it on, the index figure is ~25 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 DeepSeek R1 32B well?

Among Macs Apple sells new, the Mac Studio M5 Max (36 GB), $2,499 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with DeepSeek R1 32B, at ~19 tok/s (estimated).

Do I need to raise the GPU memory limit to run DeepSeek R1 32B?

On 2 of the 54 configurations, yes: Mac mini M2 Pro 32 GB (used), Mac Studio M2 Max 32 GB (used). macOS lets the GPU use only part of unified memory by default (about 21 GB on the Mac mini M2 Pro (32 GB)), and DeepSeek R1 32B needs about 22 GB. Running sudo sysctl iogpu.wired_limit_mb=28672 in Terminal raises the limit on a 32 GB Mac until the next restart. On iMac M6 24 GB, Mac mini M5 Pro 24 GB, Mac mini M6 24 GB and 8 more even a safely raised limit is short: expect heavy swapping, a CPU split or an out-of-memory error. From 32 GB up, every Mac Apple sells new holds it inside the default limit.

Which quantization of DeepSeek R1 32B should I use?

Q4_K_M (about 18 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 34 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 16 and 11 GB at a quality cost. The index’s reference figure (25 tok/s on an M5 Max) is for its Q4_K_M build.

How much context can DeepSeek R1 32B use on a Mac?

Its own window is 128K tokens. At macOS’s default GPU limit, the Mac mini M6 (32 GB) holds about 15K. The full window needs about 56 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 DeepSeek R1 32B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/deepseek-r1-32b/ (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.