Yes: Ternary Bonsai 2 9B runs on all 54 Macs in the LLMCheck index. It needs about 5 GB at a 4K context, 8 GB at 64K. The smallest and cheapest current Mac that runs it at 15+ tok/s is the Mac mini M6 16 GB ($899; 40 tok/s community-measured). Best measured figure: 76.5 tok/s on an M5 Pro (published).
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 | Fits (no speed figure) | — | — | 207K | — |
| MacBook Air M5 24 GB | Fits (no speed figure) | — | — | 256K (full) | — |
| MacBook Air M5 32 GB | Fits (no speed figure) | — | — | 256K (full) | — |
| MacBook Air M1 8 GB refurb | Fits (no speed figure) | — | — | 13K | — |
| MacBook Air M4 16 GB used | Fits (no speed figure) | — | — | 172K | — |
| MacBook Air M2 16 GB refurb | Fits (no speed figure) | — | — | 172K | — |
| MacBook Air M3 16 GB refurb | Fits (no speed figure) | — | — | 172K | — |
| MacBook Air M1 16 GB refurb | Fits (no speed figure) | — | — | 172K | — |
| MacBook Air M4 24 GB used | Fits (no speed figure) | — | — | 256K (full) | — |
| MacBook Air M2 24 GB refurb | Fits (no speed figure) | — | — | 256K (full) | — |
| MacBook Air M3 24 GB refurb | Fits (no speed figure) | — | — | 256K (full) | — |
| MacBook Pro | |||||
| MacBook Pro M6 16 GB | Runs | Ternary | community40 tok/s | 207K | M6 page |
| MacBook Pro M5 Pro 24 GB | Runs | PQ2_0 | sourced77 tok/s | 256K (full) | M5 Pro page |
| MacBook Pro M6 24 GB | Runs | Ternary | community40 tok/s | 256K (full) | M6 page |
| MacBook Pro M6 32 GB | Runs | Ternary | community40 tok/s | 256K (full) | M6 page |
| MacBook Pro M5 Pro 48 GB | Runs | PQ2_0 | sourced77 tok/s | 256K (full) | M5 Pro page |
| MacBook Pro M5 Max 64 GB | Fits (no speed figure) | — | — | 256K (full) | — |
| MacBook Pro M5 Pro 64 GB | Runs | PQ2_0 | sourced77 tok/s | 256K (full) | M5 Pro page |
| MacBook Pro M5 Max 128 GB | Fits (no speed figure) | — | — | 256K (full) | — |
| MacBook Pro M3 Max 64 GB refurb | Fits (no speed figure) | — | — | 256K (full) | — |
| MacBook Pro M3 Max 128 GB refurb | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac mini | |||||
| Mac mini M6 16 GB | Runs | Ternary | community40 tok/s | 207K | M6 page |
| Mac mini M5 Pro 24 GB | Runs | PQ2_0 | sourced77 tok/s | 256K (full) | M5 Pro page |
| Mac mini M6 24 GB | Runs | Ternary | community40 tok/s | 256K (full) | M6 page |
| Mac mini M6 32 GB | Runs | Ternary | community40 tok/s | 256K (full) | M6 page |
| Mac mini M5 Pro 48 GB | Runs | PQ2_0 | sourced77 tok/s | 256K (full) | M5 Pro page |
| Mac mini M5 Pro 64 GB | Runs | PQ2_0 | sourced77 tok/s | 256K (full) | M5 Pro page |
| Mac mini M2 Pro 16 GB refurb | Fits (no speed figure) | — | — | 172K | — |
| Mac mini M4 16 GB used | Fits (no speed figure) | — | — | 172K | — |
| Mac mini M4 Pro 24 GB used | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac mini M4 24 GB used | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac mini M2 Pro 32 GB refurb | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac mini M4 Pro 48 GB used | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac mini M4 Pro 64 GB used | Fits (no speed figure) | — | — | 256K (full) | — |
| iMac | |||||
| iMac M6 16 GB | Runs | Ternary | community40 tok/s | 207K | M6 page |
| iMac M6 24 GB | Runs | Ternary | community40 tok/s | 256K (full) | M6 page |
| iMac M6 32 GB | Runs | Ternary | community40 tok/s | 256K (full) | M6 page |
| Mac Studio | |||||
| Mac Studio M5 Max 36 GB | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M5 Max 48 GB | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M5 Max 64 GB | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M5 Ultra 96 GB | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M5 Max 128 GB | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M5 Ultra 256 GB | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M5 Ultra 512 GB | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M2 Max 32 GB refurb | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M1 Ultra 64 GB refurb | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M4 Max 64 GB used | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M2 Max 64 GB refurb | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M1 Ultra 128 GB refurb | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M2 Ultra 128 GB refurb | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M4 Max 128 GB used | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M2 Ultra 192 GB refurb | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M3 Ultra 256 GB used | Fits (no speed figure) | — | — | 256K (full) | — |
| Mac Studio M3 Ultra 512 GB refurb | Fits (no speed figure) | — | — | 256K (full) | — |
Context memory is computed from its config.json (config.json read from the same org's prism-ml/Ternary-Bonsai-2-9B-mlx-2bit (same architecture; the card repo has none). hybrid: full attention on 8 of 32 layers; Gated DeltaNet layers keep a constant state): about 2.1 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 use only part of unified memory by default. Ternary Bonsai 2 9B 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.
Ternary Bonsai 2 9B 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 5 GB for it at a short context.
Every published (filled square) and community (hollow circle) run the index holds for Ternary Bonsai 2 9B: 1 published, 1 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 | llama.cpp | PQ2_0 | sourced76.5 tok/s | tg128, batch 1 | 2026-10 | github.com |
| M6 | MLX | Ternary | community40.2 tok/s | 4k | 2026-10-21 | omlx.ai binned |
The quickest start is Ollama. Pull the model by its tag (checked on ollama.com, 2026-11-14; the file is about 3.2 GB):
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 40 tok/s (community run) at Ternary; keep the context at or under 207K there, or use a q8 KV cache. The bonsai-2:9b file fits there.
Step-by-step: the Ollama install guide.
Mac mini M6 (16 GB) — smallest current Mac that runs it and cheapest at 15+ tok/s, $899 new (Apple list price, checked 2026-11-14), 40 tok/s (community run).
As an Amazon Associate, LLMCheck earns from qualifying purchases. Affiliate links cost you nothing extra and never influence the verdicts.
Yes. Ternary Bonsai 2 9B needs about 5 GB of unified memory at a short (4K-token) context, so it runs on 54 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).
About 5 GB at a 4K context: the weights plus about 2 GB for the runtime. Context adds KV cache: about 6 GB in total at 32K and 8 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 77 tok/s (published figure) at PQ2_0. The best measured figure is 76.5 tok/s on an M5 Pro (published figure, PQ2_0). 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 M6 (16 GB), $899 new (Apple list price, checked 2026-11-14), is the cheapest that reaches 15 tok/s with Ternary Bonsai 2 9B, at 40 tok/s (community run).
No. On all 54 Mac configurations where Ternary Bonsai 2 9B 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.
Ternary Bonsai 2 9B 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 256K tokens. At macOS’s default GPU limit, the Mac mini M6 (16 GB) holds about 207K. The full window needs about 14 GB, which a 24 GB Mac holds at the default limit. A q8 KV cache roughly doubles these lengths.
LLMCheck. (2026). Can I run Ternary Bonsai 2 9B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/ternary-bonsai-2-9b/ (updated ). CC BY 4.0.