Run Ternary Bonsai 2 27B on M5 Max

Ternary Bonsai 2 27B runs at 47 tok/s (46.8 as recorded) on an M5 Max, a published figure reported by github.com (llama.cpp, PQ2_0, tg128, depth 0, batch 1). It needs about 9 GB of unified memory. It is Prism ML's 27.36B dense model, released under the Apache 2.0 licence.

Speed
sourced47
tok/s
First Token
—
seconds
RAM Needed
9
GB minimum
Engine
llama.cpp
of this figure
Want to run Ternary Bonsai 2 27B faster — or step up to bigger models? Find your Mac →

The figure

This is a published figure: a real run, reported by its source and linked below. The index records it as given and never adjusts it.

MetricValue
Tokens per secondsourced47 tok/s
Provenancepublished figure · github.com
QuantizationPQ2_0
Enginellama.cpp
Contexttg128, depth 0, batch 1
Figure dated2026-09-16
Minimum RAM9 GB
Parameters27.36B
Chip bandwidth614 GB/s

Every figure for Ternary Bonsai 2 27B on the M5 Max

Each row as the index holds it, with its source. “Mac RAM” is the memory of the Mac a run used, not the model’s requirement (9 GB). The headline figure follows the reference rule: the lower-median measured plain-decode run at 5 bits or fewer (a run whose quant was not stated counts only when no stated-quant run qualifies), else the estimate; a run marked “not used to anchor estimates” is listed here but never becomes the headline.

SpeedQuantEngineMac RAMContextSourceNote
sourced46.8 tok/sPQ2_0llama.cpp—tg128, depth 0, batch 1github.comVendor whitepaper Table 6: PrismML llama.cpp fork (Metal), release build, mean of 3 after warm-up; 7.21 GB. Replaces the model card's 47.0, which was labelled pre-rotation.
community43.4 tok/sTernaryMLX48 GB4komlx.ai40-core GPU. oMLX v0.7.1rc1, MTP/DFlash off; prism-ml Ternary-Bonsai-2-27B-mlx-2bit (ternary weights in MLX's 2-bit container, 2.25 bpw stored); the pack needs its bundled loader and the page does not show it was used, so it does not anchor; 14.3 GB peak. 40.3 tok/s at 8k.; not used to anchor estimates
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Setup: run Ternary Bonsai 2 27B on a Mac

Ollama — install it (brew install ollama or the app from ollama.com), then pull the model by its tag, checked on ollama.com on 2026-10-24:

ollama run bonsai-2:27b

MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:

pip install -U mlx-lm
mlx_lm.generate --model <repo-id> --prompt "Hello"

Downloads: Ollama page → · model card →

The 47 tok/s figure above came from llama.cpp at PQ2_0; other runtimes and quants run at different speeds.

Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.

Ternary Bonsai 2 27B on other Apple Silicon chips

ChipSpeedQuantEngineBandwidth
M4 Maxcommunity35 tok/sPQ2_0llama.cpp546 GB/s
M5 Prosourced28 tok/sPQ2_0llama.cpp307 GB/s
M4 Procommunity21 tok/sPQ2_0llama.cpp273 GB/s
M6community13 tok/sTernaryMLX170 GB/s
M5community12 tok/sTernaryMLX153 GB/s

About Ternary Bonsai 2 27B

Prism ML's ternary (1.58-bit) rebuild of Qwen3.8-27B (Sep 2026, Apache 2.0): ~7 GB, image input, 262K context. It keeps 98% of the base model's average on Prism's 14-benchmark suite but drops on agentic coding (SWE-bench Verified 60.8 vs 80.6 on Prism's scaffold). Ternary decoding is kernel-bound, so the index quotes measured figures only: the vendor's 46.8 tok/s on an M5 Max and 28.1 on an M5 Pro (PrismML llama.cpp fork, PQ2_0), and community runs of 34.5 on an M4 Max and 20.5 on an M4 Pro (same fork) and 43.4 on an M5 Max and 13.3 on an M6 (MLX ternary pack, oMLX); Ollama's bonsai-2:27b ships the 8.3 GB Q2_0 pack.

Apache 2.0 licence · 27.36B · 262K context · LLMCheck capability 37/50 · see its leaderboard rank →

System requirements

Macs with the M5 Max

🛒 Get a Mac that runs Ternary Bonsai 2 27B

Ternary Bonsai 2 27B needs about 9 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.

Compare More Models

See how Ternary Bonsai 2 27B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard