Can I run Bonsai 27B on a Mac?

Yes: Bonsai 27B runs on 53 of 54 Macs in the LLMCheck index. It needs about 6 GB at a 4K context, 11 GB at 64K. Smallest current Mac: the Mac mini M6 16 GB; cheapest at 15+ tok/s: the Mac mini M5 Pro 24 GB ($1,699; 44 tok/s published). Best measured figure: 66.4 tok/s on an M5 Max (published).

RAM at 4K
6
GB
RAM at 64K
11
GB, 16-bit KV
Macs that run it
53
of 54 configs
Best measured
sourced66.4
tok/s · M5 Max

Bonsai 27B 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 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).

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 shortFits (no speed figure) fits the default limit; no figure for this chipDoesn't fit needs more memory than the Mac has
MacVerdictBuildSpeedMax contextModel page
MacBook Air
MacBook Air M5 16 GBFits (no speed figure)——91K—
MacBook Air M5 24 GBFits (no speed figure)——179K—
MacBook Air M5 32 GBFits (no speed figure)——256K (full)—
MacBook Air M1 8 GB refurbOver GPU limit why ↓————
MacBook Air M4 16 GB usedFits (no speed figure)——73K—
MacBook Air M2 16 GB refurbFits (no speed figure)——73K—
MacBook Air M3 16 GB refurbFits (no speed figure)——73K—
MacBook Air M1 16 GB refurbFits (no speed figure)——73K—
MacBook Air M4 24 GB usedFits (no speed figure)——153K—
MacBook Air M2 24 GB refurbFits (no speed figure)——153K—
MacBook Air M3 24 GB refurbFits (no speed figure)——153K—
MacBook Pro
MacBook Pro M6 16 GBFits (no speed figure)——91K—
MacBook Pro M5 Pro 24 GBRunsQ1_0_g128sourced44 tok/s179KM5 Pro page
MacBook Pro M6 24 GBFits (no speed figure)——179K—
MacBook Pro M6 32 GBFits (no speed figure)——256K (full)—
MacBook Pro M5 Pro 48 GBRunsQ1_0_g128sourced44 tok/s256K (full)M5 Pro page
MacBook Pro M5 Max 64 GBRunsQ1_0_g128sourced66 tok/s256K (full)M5 Max page
MacBook Pro M5 Pro 64 GBRunsQ1_0_g128sourced44 tok/s256K (full)M5 Pro page
MacBook Pro M5 Max 128 GBRunsQ1_0_g128sourced66 tok/s256K (full)M5 Max page
MacBook Pro M3 Max 64 GB refurbFits (no speed figure)——256K (full)—
MacBook Pro M3 Max 128 GB refurbFits (no speed figure)——256K (full)—
Mac mini
Mac mini M6 16 GBFits (no speed figure)——91K—
Mac mini M5 Pro 24 GBRunsQ1_0_g128sourced44 tok/s179KM5 Pro page
Mac mini M6 24 GBFits (no speed figure)——179K—
Mac mini M6 32 GBFits (no speed figure)——256K (full)—
Mac mini M5 Pro 48 GBRunsQ1_0_g128sourced44 tok/s256K (full)M5 Pro page
Mac mini M5 Pro 64 GBRunsQ1_0_g128sourced44 tok/s256K (full)M5 Pro page
Mac mini M2 Pro 16 GB refurbFits (no speed figure)——73K—
Mac mini M4 16 GB usedFits (no speed figure)——73K—
Mac mini M4 Pro 24 GB usedRunsQ1_0_g128sourced26 tok/s153KM4 Pro page
Mac mini M4 24 GB usedFits (no speed figure)——153K—
Mac mini M2 Pro 32 GB refurbFits (no speed figure)——232K—
Mac mini M4 Pro 48 GB usedRunsQ1_0_g128sourced26 tok/s256K (full)M4 Pro page
Mac mini M4 Pro 64 GB usedRunsQ1_0_g128sourced26 tok/s256K (full)M4 Pro page
iMac
iMac M6 16 GBFits (no speed figure)——91K—
iMac M6 24 GBFits (no speed figure)——179K—
iMac M6 32 GBFits (no speed figure)——256K (full)—
Mac Studio
Mac Studio M5 Max 36 GBFits (no speed figure)——256K (full)M5 Max page
Mac Studio M5 Max 48 GBRunsQ1_0_g128sourced66 tok/s256K (full)M5 Max page
Mac Studio M5 Max 64 GBRunsQ1_0_g128sourced66 tok/s256K (full)M5 Max page
Mac Studio M5 Ultra 96 GBFits (no speed figure)——256K (full)—
Mac Studio M5 Max 128 GBRunsQ1_0_g128sourced66 tok/s256K (full)M5 Max page
Mac Studio M5 Ultra 256 GBFits (no speed figure)——256K (full)—
Mac Studio M5 Ultra 512 GBFits (no speed figure)——256K (full)—
Mac Studio M2 Max 32 GB refurbFits (no speed figure)——232K—
Mac Studio M1 Ultra 64 GB refurbFits (no speed figure)——256K (full)—
Mac Studio M4 Max 64 GB usedFits (no speed figure)——256K (full)—
Mac Studio M2 Max 64 GB refurbFits (no speed figure)——256K (full)—
Mac Studio M1 Ultra 128 GB refurbFits (no speed figure)——256K (full)—
Mac Studio M2 Ultra 128 GB refurbFits (no speed figure)——256K (full)—
Mac Studio M4 Max 128 GB usedFits (no speed figure)——256K (full)—
Mac Studio M2 Ultra 192 GB refurbFits (no speed figure)——256K (full)—
Mac Studio M3 Ultra 256 GB usedFits (no speed figure)——256K (full)—
Mac Studio M3 Ultra 512 GB refurbFits (no speed figure)——256K (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 (config.json read from the same org's prism-ml/Bonsai-27B-unpacked (same architecture; the card repo has none). hybrid: full attention on 16 of 64 layers; Gated DeltaNet layers keep a constant state): about 4.3 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 Bonsai 27B 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.

Memory by quantization

Bonsai 27B 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.

Measured runs of Bonsai 27B

Every published (filled square) and community (hollow circle) run the index holds for Bonsai 27B: 3 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.

ChipRuntimeQuantDecodeContextDateSource
M5 Max —llama.cppQ1_0_g128sourced66.4 tok/stg1282026-07huggingface.co
M5 Pro —llama.cppQ1_0_g128sourced44.2 tok/stg1282026-07huggingface.co
M4 Pro —llama.cppQ1_0_g128sourced26 tok/stg1282026-07huggingface.co

Recommended setup

The index has no verified Ollama tag for Bonsai 27B. 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 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 91K there, or use a q8 KV cache.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for Bonsai 27B

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), 44 tok/s (published figure).

As an Amazon Associate, LLMCheck earns from qualifying purchases. Affiliate links cost you nothing extra and never influence the verdicts.

FAQ: Bonsai 27B on a Mac

Can I run Bonsai 27B on a Mac?

Yes. Bonsai 27B 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).

How much RAM does Bonsai 27B need?

About 6 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 8 GB in total at 32K and 11 GB at 64K with the default 16-bit cache (about 9 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.

How fast does Bonsai 27B run on a Mac?

On an M5 Max, the chip the leaderboard quotes it on, the index figure is 66 tok/s (published figure) at Q1_0_g128. The best measured figure is 66.4 tok/s on an M5 Max (published figure, Q1_0_g128). 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 Bonsai 27B well?

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 Bonsai 27B, at 44 tok/s (published figure).

Do I need to raise the GPU memory limit to run Bonsai 27B?

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.

Which quantization of Bonsai 27B should I use?

Bonsai 27B 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.

How much context can Bonsai 27B use on a Mac?

Its own window is 256K tokens. At macOS’s default GPU limit, the Mac mini M6 (16 GB) holds about 91K. The full window needs about 23 GB, which a 32 GB Mac holds at the default limit. A q8 KV cache roughly doubles these lengths.

Cite this page

LLMCheck. (2026). Can I run Bonsai 27B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/bonsai-27b/ (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.