On memory, yes: Inkling-Small fits 11 of 54 Macs in the LLMCheck index (runtime caveat below). It needs about 96 GB at a 4K context, 98 GB at 64K. Smallest and cheapest current Mac at 15+ tok/s: the Mac Studio M5 Max 128 GB ($5,099). Flagged run (not an anchor): 79.3 tok/s on an M5 Ultra 256 GB (community).
llama.cpp support is the unmerged PR #25731 and stock mlx-lm cannot load it; the MLX builds bundle their own loader.
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 | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Pro 64 GB | Doesn't fit | — | — | — | — |
| MacBook Pro M5 Max 128 GB | Runs | Q2_K | estimated42 tok/s | 396K | — |
| MacBook Pro M3 Max 64 GB refurb | Doesn't fit | — | — | — | — |
| MacBook Pro M3 Max 128 GB refurb | Runs | 2.8 bpw | estimated29 tok/s | 4K | — |
| 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 | Doesn't fit | — | — | — | — |
| 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 | Doesn't fit | — | — | — | — |
| 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 | Doesn't fit | — | — | — | — |
| Mac Studio M5 Ultra 96 GB | Over GPU limit why ↓ | Q4_K_M | estimated49 tok/s | — | M5 Ultra page |
| Mac Studio M5 Max 128 GB | Runs | Q2_K | estimated42 tok/s | 396K | — |
| Mac Studio M5 Ultra 256 GB | Runs | Q4_K_M | estimated49 tok/s | 1M (full) | M5 Ultra page |
| Mac Studio M5 Ultra 512 GB | Runs | Q4_K_M | estimated49 tok/s | 1M (full) | M5 Ultra page |
| Mac Studio M2 Max 32 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M1 Ultra 64 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M4 Max 64 GB used | Doesn't fit | — | — | — | — |
| Mac Studio M2 Max 64 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M1 Ultra 128 GB refurb | Runs | 2.8 bpw | estimated53 tok/s | 4K | — |
| Mac Studio M2 Ultra 128 GB refurb | Runs | 2.8 bpw | estimated53 tok/s | 4K | — |
| Mac Studio M4 Max 128 GB used | Runs | 2.8 bpw | estimated38 tok/s | 4K | — |
| Mac Studio M2 Ultra 192 GB refurb | Runs | Q4_K_M | estimated34 tok/s | 1M (full) | — |
| Mac Studio M3 Ultra 256 GB used | Runs | Q4_K_M | estimated35 tok/s | 1M (full) | — |
| Mac Studio M3 Ultra 512 GB refurb | Runs | Q4_K_M | estimated35 tok/s | 1M (full) | — |
Context memory is computed from its config.json (7 global layers + 35 sliding-window layers (window 512); short-conv state constant): about 2.0 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.
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 Inkling-Small needs about 96 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=86016, 84 GB) is short of the ~96 GB it needs: expect heavy swapping, a CPU split or an out-of-memory errorWeights are 276B 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 276B parameters sit in memory although only 12B are read per token. The first row is the catalog’s own figure (about 96 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 | — | 96 GB | 97 GB | 98 GB | 128 GB |
| Q2_K | 93.8 GB | 96 GB | 97 GB | 98 GB | 128 GB |
| Q3_K_M | 135.2 GB | 137 GB | 138 GB | 139 GB | 256 GB |
| Q4_K_M | 157.3 GB | 159 GB | 160 GB | 161 GB | 256 GB |
| Q5_K_M | 196.0 GB | 198 GB | 199 GB | 200 GB | 256 GB |
| Q6_K | 226.3 GB | 228 GB | 229 GB | 230 GB | 512 GB |
| Q8_0 | 292.6 GB | 295 GB | 295 GB | 296 GB | 512 GB |
| F16 | 552.0 GB | 554 GB | 555 GB | 556 GB |
Every published (filled square) and community (hollow circle) run the index holds for Inkling-Small: 0 published, 2 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.
Before you start: llama.cpp support is the unmerged PR #25731 and stock mlx-lm cannot load it; the MLX builds bundle their own loader.
The index has no verified Ollama tag for Inkling-Small. 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 Studio M5 Max (128 GB), the smallest current Mac that runs it inside the default GPU limit, the index figure is ~42 tok/s (estimated) at Q2_K; keep the context at or under 396K there, or use a q8 KV cache.
Step-by-step: the Ollama install guide.
Mac Studio M5 Max (128 GB) — smallest current Mac that runs it and cheapest at 15+ tok/s, $5,099 new (Apple list price, checked 2026-11-14), ~42 tok/s (estimated). Amazon does not stock the Mac Studio M5 Max (128 GB): Apple builds it to order.
On memory, yes (its Mac runtime carries a caveat: llama.cpp support is the unmerged PR #25731 and stock mlx-lm cannot load it; the MLX builds bundle their own loader). Inkling-Small needs about 96 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).
About 96 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 97 GB in total at 32K and 98 GB at 64K with the default 16-bit cache (about 97 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.
On an M5 Max, the chip the leaderboard quotes it on, the index figure is ~42 tok/s (estimated) at Q2_K. The only measured runs are flagged (not an anchor), so none counts as a best figure: the highest is 79.3 tok/s on an M5 Ultra 256 GB (community run, MXFP4). 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 Inkling-Small, at ~42 tok/s (estimated).
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.
Q4_K_M (about 157 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 293 GB) is closer to full quality and needs a 512 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 135 and 94 GB at a quality cost. The index’s reference figure (42 tok/s on an M5 Max) is for its Q2_K build.
Its own window is 1M tokens. At macOS’s default GPU limit, the Mac Studio M5 Max (128 GB) holds about 396K. The full window needs about 126 GB, which a 256 GB Mac holds at the default limit. A q8 KV cache roughly doubles these lengths.
LLMCheck. (2026). Can I run Inkling-Small on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/inkling-small/ (updated ). CC BY 4.0.