Yes: Llama 4 Scout runs on 12 of the 54 Macs in the LLMCheck index. It needs about 58 GB at a 4K context. The smallest current Mac that runs it is the Mac Studio M5 Ultra 96 GB; the cheapest at 15+ tok/s is the Mac Studio M5 Max 128 GB ($5,099; ~19 tok/s est.). No measured run yet.
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).
| Mac | Verdict | Build | Speed | Max context | Model page |
|---|---|---|---|---|---|
| MacBook Air | |||||
| MacBook Air M5 16 GB | Doesn't fit | — | — | — | — |
| MacBook Air M5 24 GB | Doesn't fit | — | — | — | — |
| MacBook Air M5 32 GB | Doesn't fit | — | — | — | — |
| MacBook Air M1 8 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M4 16 GB used | Doesn't fit | — | — | — | — |
| MacBook Air M2 16 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M3 16 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M1 16 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M4 24 GB used | Doesn't fit | — | — | — | — |
| MacBook Air M2 24 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Air M3 24 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Pro | |||||
| MacBook Pro M6 16 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Pro 24 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M6 24 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M6 32 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Pro 48 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Max 64 GB | Over GPU limit why ↓ | Q4_K_M | estimated19 tok/s | — | — |
| MacBook Pro M5 Pro 64 GB | Over GPU limit why ↓ | 4.3 bpw | estimated11 tok/s | — | — |
| MacBook Pro M5 Max 128 GB | Runs | Q4_K_M | estimated19 tok/s | — | — |
| MacBook Pro M3 Max 64 GB refurb | Over GPU limit why ↓ | 4.3 bpw | estimated13 tok/s | — | — |
| MacBook Pro M3 Max 128 GB refurb | Runs, slowly | Q4_K_M | estimated13 tok/s | — | — |
| Mac mini | |||||
| Mac mini M6 16 GB | Doesn't fit | — | — | — | — |
| Mac mini M5 Pro 24 GB | Doesn't fit | — | — | — | — |
| Mac mini M6 24 GB | Doesn't fit | — | — | — | — |
| Mac mini M6 32 GB | Doesn't fit | — | — | — | — |
| Mac mini M5 Pro 48 GB | Doesn't fit | — | — | — | — |
| Mac mini M5 Pro 64 GB | Over GPU limit why ↓ | 4.3 bpw | estimated11 tok/s | — | — |
| Mac mini M2 Pro 16 GB refurb | Doesn't fit | — | — | — | — |
| Mac mini M4 16 GB used | Doesn't fit | — | — | — | — |
| Mac mini M4 Pro 24 GB used | Doesn't fit | — | — | — | — |
| Mac mini M4 24 GB used | Doesn't fit | — | — | — | — |
| Mac mini M2 Pro 32 GB refurb | Doesn't fit | — | — | — | — |
| Mac mini M4 Pro 48 GB used | Doesn't fit | — | — | — | — |
| Mac mini M4 Pro 64 GB used | Over GPU limit why ↓ | 4.3 bpw | estimated10 tok/s | — | — |
| iMac | |||||
| iMac M6 16 GB | Doesn't fit | — | — | — | — |
| iMac M6 24 GB | Doesn't fit | — | — | — | — |
| iMac M6 32 GB | Doesn't fit | — | — | — | — |
| Mac Studio | |||||
| Mac Studio M5 Max 36 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Max 48 GB | Doesn't fit | — | — | — | — |
| Mac Studio M5 Max 64 GB | Over GPU limit why ↓ | Q4_K_M | estimated19 tok/s | — | — |
| Mac Studio M5 Ultra 96 GB | Runs | Q4_K_M | estimated36 tok/s | — | — |
| Mac Studio M5 Max 128 GB | Runs | Q4_K_M | estimated19 tok/s | — | — |
| Mac Studio M5 Ultra 256 GB | Runs | Q4_K_M | estimated36 tok/s | — | — |
| Mac Studio M5 Ultra 512 GB | Runs | Q4_K_M | estimated36 tok/s | — | — |
| Mac Studio M2 Max 32 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M1 Ultra 64 GB refurb | Over GPU limit why ↓ | 4.3 bpw | estimated25 tok/s | — | — |
| Mac Studio M4 Max 64 GB used | Over GPU limit why ↓ | 4.3 bpw | estimated19 tok/s | — | — |
| Mac Studio M2 Max 64 GB refurb | Over GPU limit why ↓ | 4.3 bpw | estimated13 tok/s | — | — |
| Mac Studio M1 Ultra 128 GB refurb | Runs | Q4_K_M | estimated25 tok/s | — | — |
| Mac Studio M2 Ultra 128 GB refurb | Runs | Q4_K_M | estimated25 tok/s | — | — |
| Mac Studio M4 Max 128 GB used | Runs | Q4_K_M | estimated17 tok/s | — | — |
| Mac Studio M2 Ultra 192 GB refurb | Runs | Q4_K_M | estimated25 tok/s | — | — |
| Mac Studio M3 Ultra 256 GB used | Runs | Q4_K_M | estimated25 tok/s | — | — |
| Mac Studio M3 Ultra 512 GB refurb | Runs | Q4_K_M | estimated25 tok/s | — | — |
The index has no KV-cache figure for Llama 4 Scout yet, so the context column shows —: its minimum RAM covers a short (about 4K-token) prompt only.
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 Llama 4 Scout needs about 58 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.
sudo sysctl iogpu.wired_limit_mb=57344, 56 GB) is short of the ~58 GB it needs: expect heavy swapping, a CPU split or an out-of-memory errorsudo sysctl iogpu.wired_limit_mb=57344, 56 GB) is short of the ~58 GB it needs: expect heavy swapping, a CPU split or an out-of-memory errorWeights are 109B 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 109B parameters sit in memory although only 17B are read per token. The first row is the catalog’s own figure (about 58 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.
| Build | Weights | RAM at 4K | at 32K | at 64K | Smallest Mac |
|---|---|---|---|---|---|
| As catalogued | — | 58 GB | — | — | 96 GB |
| Q2_K | 37.1 GB | 39 GB | — | — | 64 GB |
| Q3_K_M | 53.4 GB | 55 GB | — | — | 96 GB |
| Q4_K_M | 62.1 GB | 64 GB | — | — | 96 GB |
| Q5_K_M | 77.4 GB | 79 GB | — | — | 128 GB |
| Q6_K | 89.4 GB | 91 GB | — | — | 128 GB |
| Q8_0 | 115.5 GB | 118 GB | — | — | 256 GB |
| F16 | 218.0 GB | 220 GB | — | — | 256 GB |
The index holds no published or community run of Llama 4 Scout 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 →
The quickest start is Ollama. Pull the model by its tag (checked on ollama.com, 2026-11-14; the file is about 67 GB):
Prefer a window to a terminal? LM Studio downloads the same model with one click. · model card →
On the Mac Studio M5 Ultra (96 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is ~36 tok/s (estimated) at Q4_K_M; keep the context at or under a short prompt there, or use a q8 KV cache. The llama4:scout file fits there.
Step-by-step: the Ollama install guide.
Mac Studio M5 Ultra (96 GB) — smallest current Mac that runs it, $5,499 new (Apple list price, checked 2026-11-14), ~36 tok/s (estimated). Mac Studio M5 Max (128 GB) — cheapest at 15+ tok/s, $5,099 new (Apple list price, checked 2026-11-14), ~19 tok/s (estimated). Amazon does not stock the Mac Studio M5 Ultra (96 GB): Apple builds it to order. Amazon does not stock the Mac Studio M5 Max (128 GB): Apple builds it to order.
Yes. Llama 4 Scout needs about 58 GB of unified memory at a short (4K-token) context, so it runs on 12 of the 54 Mac configurations in the LLMCheck index. On 9 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 Ultra (96 GB).
About 58 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 Llama 4 Scout yet, so it cannot say how much a long context adds.
On an M5 Max, the chip the leaderboard quotes it on, the index figure is ~19 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.
Among Macs Apple sells new, the Mac Studio M5 Max (128 GB), $5,099 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Llama 4 Scout, at ~19 tok/s (estimated).
On Mac mini M5 Pro 64 GB, Mac Studio M5 Max 64 GB, MacBook Pro M5 Max 64 GB and 6 more even a safely raised limit is short: expect heavy swapping, a CPU split or an out-of-memory error. From 96 GB up, every Mac Apple sells new holds it inside the default limit.
Q4_K_M (about 62 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 116 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 53 and 37 GB at a quality cost. The index’s reference figure (19 tok/s on an M5 Max) is for its Q4_K_M build.
LLMCheck. (2026). Can I run Llama 4 Scout on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/llama-4-scout/ (updated ). CC BY 4.0.