Can I run Ternary Bonsai 2 27B on a Mac?

Yes: Ternary Bonsai 2 27B runs on 53 of the 54 Macs in the LLMCheck index. It needs about 9 GB at a 4K context, 14 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: 46.8 tok/s on an M5 Max (published figure, PQ2_0).

RAM at 4K
9
GB
RAM at 64K
14
GB, 16-bit KV
Macs that run it
53
of 54 configs
Best measured
sourced46.8
tok/s · M5 Max

Ternary Bonsai 2 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)Fits (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 GBRuns, slowlyTernarycommunity12 tok/s46KM5 page
MacBook Air M5 24 GBRuns, slowlyTernarycommunity12 tok/s134KM5 page
MacBook Air M5 32 GBRuns, slowlyTernarycommunity12 tok/s241KM5 page
MacBook Air M1 8 GB refurbDoesn't fit————
MacBook Air M4 16 GB usedFits (no speed figure)——28K—
MacBook Air M2 16 GB refurbFits (no speed figure)——28K—
MacBook Air M3 16 GB refurbFits (no speed figure)——28K—
MacBook Air M1 16 GB refurbFits (no speed figure)——28K—
MacBook Air M4 24 GB usedFits (no speed figure)——108K—
MacBook Air M2 24 GB refurbFits (no speed figure)——108K—
MacBook Air M3 24 GB refurbFits (no speed figure)——108K—
MacBook Pro
MacBook Pro M6 16 GBFits (no speed figure)——46KM6 page
MacBook Pro M5 Pro 24 GBRunsPQ2_0sourced28 tok/s134KM5 Pro page
MacBook Pro M6 24 GBRuns, slowlyTernarycommunity13 tok/s134KM6 page
MacBook Pro M6 32 GBRuns, slowlyTernarycommunity13 tok/s241KM6 page
MacBook Pro M5 Pro 48 GBRunsPQ2_0sourced28 tok/s256K (full)M5 Pro page
MacBook Pro M5 Max 64 GBRunsPQ2_0sourced47 tok/s256K (full)M5 Max page
MacBook Pro M5 Pro 64 GBRunsPQ2_0sourced28 tok/s256K (full)M5 Pro page
MacBook Pro M5 Max 128 GBRunsPQ2_0sourced47 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)——46KM6 page
Mac mini M5 Pro 24 GBRunsPQ2_0sourced28 tok/s134KM5 Pro page
Mac mini M6 24 GBRuns, slowlyTernarycommunity13 tok/s134KM6 page
Mac mini M6 32 GBRuns, slowlyTernarycommunity13 tok/s241KM6 page
Mac mini M5 Pro 48 GBRunsPQ2_0sourced28 tok/s256K (full)M5 Pro page
Mac mini M5 Pro 64 GBRunsPQ2_0sourced28 tok/s256K (full)M5 Pro page
Mac mini M2 Pro 16 GB refurbFits (no speed figure)——28K—
Mac mini M4 16 GB usedFits (no speed figure)——28K—
Mac mini M4 Pro 24 GB usedRunsPQ2_0community21 tok/s108KM4 Pro page
Mac mini M4 24 GB usedFits (no speed figure)——108K—
Mac mini M2 Pro 32 GB refurbFits (no speed figure)——187K—
Mac mini M4 Pro 48 GB usedRunsPQ2_0community21 tok/s256K (full)M4 Pro page
Mac mini M4 Pro 64 GB usedRunsPQ2_0community21 tok/s256K (full)M4 Pro page
iMac
iMac M6 16 GBFits (no speed figure)——46KM6 page
iMac M6 24 GBRuns, slowlyTernarycommunity13 tok/s134KM6 page
iMac M6 32 GBRuns, slowlyTernarycommunity13 tok/s241KM6 page
Mac Studio
Mac Studio M5 Max 36 GBFits (no speed figure)——256K (full)M5 Max page
Mac Studio M5 Max 48 GBRunsPQ2_0sourced47 tok/s256K (full)M5 Max page
Mac Studio M5 Max 64 GBRunsPQ2_0sourced47 tok/s256K (full)M5 Max page
Mac Studio M5 Ultra 96 GBFits (no speed figure)——256K (full)—
Mac Studio M5 Max 128 GBRunsPQ2_0sourced47 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)——187K—
Mac Studio M1 Ultra 64 GB refurbFits (no speed figure)——256K (full)—
Mac Studio M4 Max 64 GB usedRunsPQ2_0community35 tok/s256K (full)M4 Max page
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 usedRunsPQ2_0community35 tok/s256K (full)M4 Max page
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/Ternary-Bonsai-2-27B-mlx-2bit (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.

macOS’s GPU memory limit

macOS lets the GPU use only part of unified memory by default. Ternary Bonsai 2 27B fits inside that default limit on every Mac it fits at all, so no Mac in the table needs it raised at a short context. Long contexts may still need it: the context column already uses each Mac’s default limit.

Memory by quantization

Ternary Bonsai 2 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 9 GB for it at a short context.

Measured runs of Ternary Bonsai 2 27B

Every published (filled square) and community (hollow circle) run the index holds for Ternary Bonsai 2 27B: 2 published, 7 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.cppPQ2_0sourced46.8 tok/stg128, depth 0, batch 12026-09-16github.com
M5 Max 128 GBMLXTernarycommunity44.3 tok/s1k2026-11-13omlx.ai not an anchor
M5 Max 48 GBMLXTernarycommunity43.4 tok/s4k2026-10-20omlx.ai not an anchor
M4 Max 128 GBllama.cppPQ2_0community34.5 tok/s~2.2K-token prompts, 320 generated, temperature 0, mean of 32026-09-17github.com not an anchor
M5 Pro —llama.cppPQ2_0sourced28.1 tok/stg128, depth 0, batch 12026-09huggingface.co
M5 Pro 48 GBMLXTernarycommunity23.6 tok/s1k2026-10-19omlx.ai not an anchor
M4 Pro 64 GBllama.cppPQ2_0community20.53 tok/stg128, 3 reps2026-09-22github.com not an anchor
M6 32 GBMLXTernarycommunity13.3 tok/s4k2026-10-23omlx.ai not an anchor
M5 32 GBMLXTernarycommunity12 tok/s1k2026-10-04omlx.ai not an anchor

Recommended setup

The quickest start is Ollama. Pull the model by its tag (checked on ollama.com, 2026-11-14; the file is about 8.3 GB):

ollama run bonsai-2:27b

Prefer a window to a terminal? LM Studio downloads the same model with one click. · model card →

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 46K there, or use a q8 KV cache. The bonsai-2:27b file fits there.

Step-by-step: the Ollama install guide.

🛒 Which Mac to get for Ternary Bonsai 2 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), 28 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: Ternary Bonsai 2 27B on a Mac

Can I run Ternary Bonsai 2 27B on a Mac?

Yes. Ternary Bonsai 2 27B needs about 9 GB of unified memory at a short (4K-token) context, so it runs on 53 of the 54 Mac configurations in the LLMCheck index. The smallest Mac Apple sells new that runs it is the Mac mini M6 (16 GB).

How much RAM does Ternary Bonsai 2 27B need?

About 9 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 11 GB in total at 32K and 14 GB at 64K with the default 16-bit cache (about 12 GB at 64K with a q8 cache). These are estimates from the model’s config.json, not measurements.

How fast does Ternary Bonsai 2 27B run on a Mac?

On an M5 Max, the chip the leaderboard quotes it on, the index figure is 47 tok/s (published figure) at PQ2_0. The best measured figure is 46.8 tok/s on an M5 Max (published figure, PQ2_0). 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 Ternary Bonsai 2 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 Ternary Bonsai 2 27B, at 28 tok/s (published figure).

Do I need to raise the GPU memory limit to run Ternary Bonsai 2 27B?

No. On all 53 Mac configurations where Ternary Bonsai 2 27B fits, it fits inside that Mac’s default GPU memory limit at a short context; only a long context on the smallest of them can push it over.

Which quantization of Ternary Bonsai 2 27B should I use?

Ternary Bonsai 2 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 Ternary Bonsai 2 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 46K. The full window needs about 26 GB, which a 36 GB Mac holds at the default limit. A q8 KV cache roughly doubles these lengths.

Cite this page

LLMCheck. (2026). Can I run Ternary Bonsai 2 27B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/ternary-bonsai-2-27b/ (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.