On memory, yes: Maple Preview 20B-A1B fits 53 of 54 Macs in the LLMCheck index (runtime caveat below). It needs about 6 GB at a 4K context, 7 GB at 64K. Smallest current Mac: Mac mini M6 16 GB; cheapest at 15+ tok/s: Mac mini M5 Pro 24 GB, $1,699. Best measured figure: 387 tok/s on an M5 Pro (published).
Runs only through DeepGrove's own forks (mlx-lm-deepgrove, deepgrove-ai/llama.cpp); its cards name no stock llama.cpp, mlx-lm, LM Studio or Ollama route.
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 small mixture-of-experts models (40B total or less), the formula’s typical error is about 15% (the median gap to 88 measured plain-decode runs; it tends to undershoot (median −7%), 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 | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Air M5 24 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Air M5 32 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Air M1 8 GB refurb | Over GPU limit why ↓ | — | — | — | — |
| MacBook Air M4 16 GB used | Runs | Ternary | sourced169 tok/s | 128K (full) | M4 page |
| MacBook Air M2 16 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Air M3 16 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Air M1 16 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Air M4 24 GB used | Runs | Ternary | sourced169 tok/s | 128K (full) | M4 page |
| MacBook Air M2 24 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Air M3 24 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Pro | |||||
| MacBook Pro M6 16 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Pro M5 Pro 24 GB | Runs | Ternary | sourced387 tok/s | 128K (full) | M5 Pro page |
| MacBook Pro M6 24 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Pro M6 32 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Pro M5 Pro 48 GB | Runs | Ternary | sourced387 tok/s | 128K (full) | M5 Pro page |
| MacBook Pro M5 Max 64 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Pro M5 Pro 64 GB | Runs | Ternary | sourced387 tok/s | 128K (full) | M5 Pro page |
| MacBook Pro M5 Max 128 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Pro M3 Max 64 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| MacBook Pro M3 Max 128 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac mini | |||||
| Mac mini M6 16 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac mini M5 Pro 24 GB | Runs | Ternary | sourced387 tok/s | 128K (full) | M5 Pro page |
| Mac mini M6 24 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac mini M6 32 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac mini M5 Pro 48 GB | Runs | Ternary | sourced387 tok/s | 128K (full) | M5 Pro page |
| Mac mini M5 Pro 64 GB | Runs | Ternary | sourced387 tok/s | 128K (full) | M5 Pro page |
| Mac mini M2 Pro 16 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac mini M4 16 GB used | Runs | Ternary | sourced169 tok/s | 128K (full) | M4 page |
| Mac mini M4 Pro 24 GB used | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac mini M4 24 GB used | Runs | Ternary | sourced169 tok/s | 128K (full) | M4 page |
| Mac mini M2 Pro 32 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac mini M4 Pro 48 GB used | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac mini M4 Pro 64 GB used | Fits (no speed figure) | — | — | 128K (full) | — |
| iMac | |||||
| iMac M6 16 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| iMac M6 24 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| iMac M6 32 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio | |||||
| Mac Studio M5 Max 36 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M5 Max 48 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M5 Max 64 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M5 Ultra 96 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M5 Max 128 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M5 Ultra 256 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M5 Ultra 512 GB | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M2 Max 32 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M1 Ultra 64 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M4 Max 64 GB used | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M2 Max 64 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M1 Ultra 128 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M2 Ultra 128 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M4 Max 128 GB used | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M2 Ultra 192 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M3 Ultra 256 GB used | Fits (no speed figure) | — | — | 128K (full) | — |
| Mac Studio M3 Ultra 512 GB refurb | Fits (no speed figure) | — | — | 128K (full) | — |
Context memory is computed from its config.json (6 full layers + 18 sliding-window layers (window 512)): about 0.8 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 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 Maple Preview 20B-A1B needs about 6 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.
Maple Preview 20B-A1B ships as a sub-2-bit / ternary build, which decodes through its own kernels; the GGUF quant ladder (Q2_K…F16) does not describe it. The index needs about 6 GB for it at a short context.
Every published (filled square) and community (hollow circle) run the index holds for Maple Preview 20B-A1B: 2 published, 0 community, each linked to its source. LLMCheck runs no tests of its own. One row is one measurement session; on each chip the table above shows the lower median of the eligible runs (plain decode at 5 bits or fewer), and a binned or “not an anchor” run is shown but never used as a reference.
| Chip | Runtime | Quant | Decode | Context | Date | Source |
|---|---|---|---|---|---|---|
| M5 Pro | MLX | Ternary | sourced387 tok/s | 512-token prompt, 256 generated | 2026-09-17 | github.com |
| M4 | MLX | Ternary | sourced169 tok/s | — | 2026-08 | github.com |
Before you start: Runs only through DeepGrove's own forks (mlx-lm-deepgrove, deepgrove-ai/llama.cpp); its cards name no stock llama.cpp, mlx-lm, LM Studio or Ollama route.
The index has no verified Ollama tag for Maple Preview 20B-A1B. Start from its listing and copy the exact name of a build that fits: Hugging Face repo → · 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 not available; keep the context at or under 128K there, or use a q8 KV cache.
Step-by-step: the Ollama install guide.
Mac mini M6 (16 GB) — smallest current Mac that runs it, $899 new (Apple list price, checked 2026-11-14). Mac mini M5 Pro (24 GB) — cheapest at 15+ tok/s, $1,699 new (Apple list price, checked 2026-11-14), 387 tok/s (published figure).
As an Amazon Associate, LLMCheck earns from qualifying purchases. Affiliate links cost you nothing extra and never influence the verdicts.
On memory, yes (its Mac runtime carries a caveat: Runs only through DeepGrove's own forks (mlx-lm-deepgrove, deepgrove-ai/llama.cpp); its cards name no stock llama.cpp, mlx-lm, LM Studio or Ollama route). Maple Preview 20B-A1B needs about 6 GB of unified memory at a short (4K-token) context, so it runs on 53 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 mini M6 (16 GB).
About 6 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 7 GB in total at 32K and 7 GB at 64K with the default 16-bit cache (about 7 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.
On an M5 Pro, the chip the leaderboard quotes it on, the index figure is 387 tok/s (published figure) at Ternary. The best measured figure is 387 tok/s on an M5 Pro 48 GB (published figure, Ternary). 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 mini M5 Pro (24 GB), $1,699 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Maple Preview 20B-A1B, at 387 tok/s (published figure).
On MacBook Air M1 8 GB (used) even a safely raised limit is short: expect heavy swapping, a CPU split or an out-of-memory error. From 16 GB up, every Mac Apple sells new holds it inside the default limit.
Maple Preview 20B-A1B ships as a sub-2-bit / ternary build with its own kernels, so the usual GGUF ladder (Q2_K to F16) does not apply: use the published build.
Its own window is 128K tokens. At macOS’s default GPU limit, the Mac mini M6 (16 GB) holds about 128K (the full window).
LLMCheck. (2026). Can I run Maple Preview 20B-A1B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/maple-preview-20b-a1b/ (updated ). CC BY 4.0.