Yes: Ripple-65B Preview runs on 25 of 54 Macs in the LLMCheck index. It needs about 33 GB at a 4K context, 38 GB at 64K. Smallest current Mac: Mac mini M5 Pro 48 GB; cheapest at 15+ tok/s: Mac Studio M5 Ultra 96 GB, $5,499. Flagged run (not an anchor): 23.3 tok/s on an M5 Ultra 256 GB (community).
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).
| 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 | Runs, slowly | Q4_K_M | estimated7 tok/s | 70K | — |
| MacBook Pro M5 Max 64 GB | Runs, slowly | Q4_K_M | estimated13 tok/s | 284K | M5 Max page |
| MacBook Pro M5 Pro 64 GB | Runs, slowly | Q4_K_M | estimated7 tok/s | 284K | — |
| MacBook Pro M5 Max 128 GB | Runs, slowly | Q4_K_M | estimated13 tok/s | 1M (full) | M5 Max page |
| MacBook Pro M3 Max 64 GB refurb | Runs, slowly | Q4_K_M | estimated9 tok/s | 227K | — |
| MacBook Pro M3 Max 128 GB refurb | Runs, slowly | Q4_K_M | estimated9 tok/s | 942K | — |
| 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 | Runs, slowly | Q4_K_M | estimated7 tok/s | 70K | — |
| Mac mini M5 Pro 64 GB | Runs, slowly | Q4_K_M | estimated7 tok/s | 284K | — |
| 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 | Runs, slowly | Q4_K_M | estimated6 tok/s | 48K | M4 Pro page |
| Mac mini M4 Pro 64 GB used | Runs, slowly | Q4_K_M | estimated6 tok/s | 227K | M4 Pro page |
| 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 | Over GPU limit why ↓ | 4.0 bpw | estimated12 tok/s | — | M5 Max page |
| Mac Studio M5 Max 48 GB | Runs, slowly | Q4_K_M | estimated13 tok/s | 70K | M5 Max page |
| Mac Studio M5 Max 64 GB | Runs, slowly | Q4_K_M | estimated13 tok/s | 284K | M5 Max page |
| Mac Studio M5 Ultra 96 GB | Runs | Q4_K_M | estimated26 tok/s | 670K | M5 Ultra page |
| Mac Studio M5 Max 128 GB | Runs, slowly | Q4_K_M | estimated13 tok/s | 1M (full) | M5 Max page |
| Mac Studio M5 Ultra 256 GB | Runs | Q4_K_M | estimated26 tok/s | 1M (full) | M5 Ultra page |
| Mac Studio M5 Ultra 512 GB | Runs | Q4_K_M | estimated26 tok/s | 1M (full) | M5 Ultra page |
| Mac Studio M2 Max 32 GB refurb | Doesn't fit | — | — | — | — |
| Mac Studio M1 Ultra 64 GB refurb | Runs | Q4_K_M | estimated17 tok/s | 227K | — |
| Mac Studio M4 Max 64 GB used | Runs, slowly | Q4_K_M | estimated12 tok/s | 227K | M4 Max page |
| Mac Studio M2 Max 64 GB refurb | Runs, slowly | Q4_K_M | estimated9 tok/s | 227K | — |
| Mac Studio M1 Ultra 128 GB refurb | Runs | Q4_K_M | estimated17 tok/s | 942K | — |
| Mac Studio M2 Ultra 128 GB refurb | Runs | Q4_K_M | estimated17 tok/s | 942K | — |
| Mac Studio M4 Max 128 GB used | Runs, slowly | Q4_K_M | estimated12 tok/s | 942K | M4 Max page |
| Mac Studio M2 Ultra 192 GB refurb | Runs | Q4_K_M | estimated17 tok/s | 1M (full) | — |
| Mac Studio M3 Ultra 256 GB used | Runs | Q4_K_M | estimated17 tok/s | 1M (full) | M3 Ultra page |
| Mac Studio M3 Ultra 512 GB refurb | Runs | Q4_K_M | estimated17 tok/s | 1M (full) | M3 Ultra page |
Context memory is computed from its config.json (16 full layers + 64 sliding-window layers (window 1024)): about 4.6 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 Ripple-65B Preview needs about 33 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=32256, 32 GB) is short of the ~33 GB it needs: expect heavy swapping, a CPU split or an out-of-memory errorWeights are 64.8B 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 33 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 | — | 33 GB | 35 GB | 37 GB | 48 GB |
| Q2_K | 22.0 GB | 24 GB | 26 GB | 28 GB | 32 GB |
| Q3_K_M | 31.8 GB | 34 GB | 36 GB | 38 GB | 48 GB |
| Q4_K_M | 36.9 GB | 39 GB | 41 GB | 43 GB | 64 GB |
| Q5_K_M | 46.0 GB | 48 GB | 50 GB | 52 GB | 64 GB |
| Q6_K | 53.1 GB | 55 GB | 57 GB | 59 GB | 96 GB |
| Q8_0 | 68.7 GB | 71 GB | 73 GB | 75 GB | 96 GB |
| F16 | 129.6 GB | 132 GB | 133 GB | 136 GB | 256 GB |
Every published (filled square) and community (hollow circle) run the index holds for Ripple-65B Preview: 0 published, 6 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 Ultra | MLX | 4-bit | community23.3 tok/s | 1K context, one stream | 2026-11-04 | huggingface.co not an anchor |
| M5 Ultra | MLX | 8-bit | community13.6 tok/s | 1k | 2026-11-07 | omlx.ai not an anchor |
| M5 Ultra | MLX | 8-bit | community12.8 tok/s | 1K context, one stream | 2026-11-05 | huggingface.co not an anchor |
| M3 Ultra | MLX | 4-bit | community17.2 tok/s | 1k | 2026-11-07 | omlx.ai not an anchor |
| M4 Max | MLX | 8-bit | community6.8 tok/s | 1k | 2026-11-12 | omlx.ai not an anchor |
| M4 Pro | MLX | 4-bit | community6.2 tok/s | 1k | 2026-11-09 | omlx.ai not an anchor |
The quickest start is Ollama. Pull the model by its tag (checked on ollama.com, 2026-11-14; the file is about 46 GB):
Prefer a window to a terminal? LM Studio downloads the same model with one click. · model card →
On the Mac mini M5 Pro (48 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 70K there, or use a q8 KV cache. Note: the ripple-preview:65b tag is about 46 GB, so it needs a 64 GB Mac; on 48 GB use a ~5-bit build after raising the GPU limit.
Step-by-step: the Ollama install guide.
Mac mini M5 Pro (48 GB) — smallest current Mac that runs it, $2,299 new (Apple list price, checked 2026-11-14), ~7 tok/s (estimated). For Ollama: the ripple-preview:65b tag is about 46 GB, so it needs a 64 GB Mac; on 48 GB use a ~5-bit build after raising the GPU limit. Mac Studio M5 Ultra (96 GB) — cheapest at 15+ tok/s, $5,499 new (Apple list price, checked 2026-11-14), ~26 tok/s (estimated). Amazon does not stock the Mac mini M5 Pro (48 GB): Apple builds it to order. Amazon does not stock the Mac Studio M5 Ultra (96 GB): Apple builds it to order.
Yes. Ripple-65B Preview needs about 33 GB of unified memory at a short (4K-token) context, so it runs on 25 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 M5 Pro (48 GB).
About 33 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 35 GB in total at 32K and 38 GB at 64K with the default 16-bit cache (about 36 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 ~13 tok/s (estimated) at Q4_K_M. The only measured runs are flagged (not an anchor), so none counts as a best figure: the highest is 23.3 tok/s on an M5 Ultra 256 GB (community run, 4-bit). 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 Ultra (96 GB), $5,499 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Ripple-65B Preview, at ~26 tok/s (estimated).
On Mac Studio M5 Max 36 GB even a safely raised limit is short: expect heavy swapping, a CPU split or an out-of-memory error. From 48 GB up, every Mac Apple sells new holds it inside the default limit.
Q4_K_M (about 37 GB of weights) is the common 4-bit GGUF choice. Q8_0 (about 69 GB) is closer to full quality and needs a 96 GB Mac at the default GPU limit. Q3_K_M and Q2_K shrink it to about 32 and 22 GB at a quality cost. The index’s reference figure (13 tok/s on an M5 Max) is for its Q4_K_M build.
Its own window is 1M tokens. At macOS’s default GPU limit, the Mac mini M5 Pro (48 GB) holds about 70K. The full window needs about 102 GB, which a 128 GB Mac holds at the default limit. A q8 KV cache roughly doubles these lengths.
LLMCheck. (2026). Can I run Ripple-65B Preview on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/ripple-65b-preview/ (updated ). CC BY 4.0.