Can I run Mixtral 8x22B on a Mac?

Yes: Mixtral 8x22B runs on 11 of 54 Macs in the LLMCheck index. It needs about 88 GB of unified memory at a 4K context and about 103 GB at 64K. Smallest current Mac: the Mac Studio M5 Max 128 GB; cheapest at 15+ tok/s: the Mac Studio M5 Ultra 256 GB ($9,499; ~17 tok/s est.). No measured run yet.

RAM at 4K
88
GB
RAM at 64K
103
GB, 16-bit KV
Macs that run it
11
of 54 configs
Best measured
—
no measured run

Mixtral 8x22B 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 large mixture-of-experts models (over 40B total), the formula’s typical error is about 34% (the median gap to 70 measured plain-decode runs; it tends to undershoot (median −33%), 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 GBDoesn't fit————
MacBook Air M5 32 GBDoesn't fit————
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 usedDoesn't fit————
MacBook Air M2 24 GB refurbDoesn't fit————
MacBook Air M3 24 GB refurbDoesn't fit————
MacBook Pro
MacBook Pro M6 16 GBDoesn't fit————
MacBook Pro M5 Pro 24 GBDoesn't fit————
MacBook Pro M6 24 GBDoesn't fit————
MacBook Pro M6 32 GBDoesn't fit————
MacBook Pro M5 Pro 48 GBDoesn't fit————
MacBook Pro M5 Max 64 GBDoesn't fit————
MacBook Pro M5 Pro 64 GBDoesn't fit————
MacBook Pro M5 Max 128 GBRuns, slowlyQ4_K_Mestimated9 tok/s64K (full)—
MacBook Pro M3 Max 64 GB refurbDoesn't fit————
MacBook Pro M3 Max 128 GB refurbRuns, slowlyQ4_K_Mestimated6 tok/s38K—
Mac mini
Mac mini M6 16 GBDoesn't fit————
Mac mini M5 Pro 24 GBDoesn't fit————
Mac mini M6 24 GBDoesn't fit————
Mac mini M6 32 GBDoesn't fit————
Mac mini M5 Pro 48 GBDoesn't fit————
Mac mini M5 Pro 64 GBDoesn't fit————
Mac mini M2 Pro 16 GB refurbDoesn't fit————
Mac mini M4 16 GB usedDoesn't fit————
Mac mini M4 Pro 24 GB usedDoesn't fit————
Mac mini M4 24 GB usedDoesn't fit————
Mac mini M2 Pro 32 GB refurbDoesn't fit————
Mac mini M4 Pro 48 GB usedDoesn't fit————
Mac mini M4 Pro 64 GB usedDoesn't fit————
iMac
iMac M6 16 GBDoesn't fit————
iMac M6 24 GBDoesn't fit————
iMac M6 32 GBDoesn't fit————
Mac Studio
Mac Studio M5 Max 36 GBDoesn't fit————
Mac Studio M5 Max 48 GBDoesn't fit————
Mac Studio M5 Max 64 GBDoesn't fit————
Mac Studio M5 Ultra 96 GBOver GPU limit why ↓Q4_K_Mestimated17 tok/s——
Mac Studio M5 Max 128 GBRuns, slowlyQ4_K_Mestimated9 tok/s64K (full)—
Mac Studio M5 Ultra 256 GBRunsQ4_K_Mestimated17 tok/s64K (full)—
Mac Studio M5 Ultra 512 GBRunsQ4_K_Mestimated17 tok/s64K (full)—
Mac Studio M2 Max 32 GB refurbDoesn't fit————
Mac Studio M1 Ultra 64 GB refurbDoesn't fit————
Mac Studio M4 Max 64 GB usedDoesn't fit————
Mac Studio M2 Max 64 GB refurbDoesn't fit————
Mac Studio M1 Ultra 128 GB refurbRuns, slowlyQ4_K_Mestimated11 tok/s38K—
Mac Studio M2 Ultra 128 GB refurbRuns, slowlyQ4_K_Mestimated11 tok/s38K—
Mac Studio M4 Max 128 GB usedRuns, slowlyQ4_K_Mestimated8 tok/s38K—
Mac Studio M2 Ultra 192 GB refurbRuns, slowlyQ4_K_Mestimated11 tok/s64K (full)—
Mac Studio M3 Ultra 256 GB usedRuns, slowlyQ4_K_Mestimated12 tok/s64K (full)—
Mac Studio M3 Ultra 512 GB refurbRuns, slowlyQ4_K_Mestimated12 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 (GQA on all 56 layers (8 kv heads x 128)): about 15.0 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 Mixtral 8x22B needs about 88 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.

Mixtral 8x22B: memory by quantization

Weights are 141B 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 141B parameters sit in memory although only 39B are read per token. The first row is the catalog’s own figure (about 88 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—88 GB95 GB102 GB128 GB
Q2_K47.9 GB50 GB57 GB64 GB64 GB
Q3_K_M69.1 GB71 GB78 GB85 GB96 GB
Q4_K_M80.4 GB82 GB89 GB96 GB128 GB (96 GB with a raised limit)
Q5_K_M100.1 GB102 GB109 GB116 GB128 GB
Q6_K115.6 GB118 GB124 GB132 GB256 GB
Q8_0149.5 GB151 GB158 GB166 GB256 GB
F16282.0 GB284 GB291 GB298 GB512 GB

Measured runs

The index holds no published or community run of Mixtral 8x22B 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 80 GB):

ollama run mixtral:8x22b

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

On the Mac Studio M5 Max (128 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is ~9 tok/s (estimated) at Q4_K_M; keep the context at or under 64K there, or use a q8 KV cache. The mixtral:8x22b file fits there.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for Mixtral 8x22B

Mac Studio M5 Max (128 GB) — smallest current Mac that runs it, $5,099 new (Apple list price, checked 2026-11-14), ~9 tok/s (estimated). Mac Studio M5 Ultra (256 GB) — cheapest at 15+ tok/s, $9,499 new (Apple list price, checked 2026-11-14), ~17 tok/s (estimated). Amazon does not stock the Mac Studio M5 Max (128 GB): Apple builds it to order. Amazon does not stock the Mac Studio M5 Ultra (256 GB): Apple builds it to order.

FAQ: Mixtral 8x22B on a Mac

Can I run Mixtral 8x22B on a Mac?

Yes. Mixtral 8x22B needs about 88 GB of unified memory at a short (4K-token) context, so it runs on 11 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 Studio M5 Max (128 GB).

How much RAM does Mixtral 8x22B need?

About 88 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 95 GB in total at 32K and 103 GB at 64K with the default 16-bit cache (about 96 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.

How fast does Mixtral 8x22B run on a Mac?

On an M5 Max, the chip the leaderboard quotes it on, the index figure is ~9 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 Mixtral 8x22B well?

Among Macs Apple sells new, the Mac Studio M5 Ultra (256 GB), $9,499 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Mixtral 8x22B, at ~17 tok/s (estimated).

Do I need to raise the GPU memory limit to run Mixtral 8x22B?

On Mac Studio M5 Ultra 96 GB even a safely raised limit is short: expect heavy swapping, a CPU split or an out-of-memory error. From 128 GB up, every Mac Apple sells new holds it inside the default limit.

Which quantization of Mixtral 8x22B should I use?

Q4_K_M (about 80 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 149 GB) is closer to full quality and needs a 256 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 69 and 48 GB at a quality cost. The index’s reference figure (9 tok/s on an M5 Max) is for its Q4_K_M build.

How much context can Mixtral 8x22B use on a Mac?

Its own window is 64K tokens. At macOS’s default GPU limit, the Mac Studio M5 Max (128 GB) holds about 64K (the full window).

Cite this page

LLMCheck. (2026). Can I run Mixtral 8x22B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/mixtral-8x22b/ (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.