Can Ternary Bonsai 27B run on MacBook Pro M5 Pro 64GB?

YES — Runs great

Q2_0 · 4K context · formula estimate

What this means

Ternary Bonsai 27B fits on the MacBook Pro M5 Pro · 64GB at Q2_0. We estimate it uses 8.6GB of the conservative 57.6GB working budget.

Estimated decode speed is 21.3–29.8 tokens/s. A roughly 300-word answer may take around 16 seconds.

View technical details ↓Setup guide →

21.3–29.8tokens/s

estimated · instant

8.6GB

needed at Q2_0

Q2_0

quant selected

49GB

working headroom

needs 8.6 GBworking budget 57.6 GB

Apple M5 Pro64 GB unified memoryMetalActive cooling

See how fast it feels

Using the midpoint of our 21.3–29.8 tokens/s estimate for this demo.

Live demo · 25.6 tokens/s

▌

Compare other speeds →

Where the memory goes

Component	Detail	GB
Model weights	Q2_0 GGUF (7.2 GB) + mmap overhead	7.6
KV cache	4K context window	0.3
Runtime	macOS inference app + compute buffers	0.8
Total needed	Q2_0, 4K context	8.6
Working budget	64 GB unified memory − conservative macOS reserve	57.6
Headroom	remaining inside the working budget	49

Pick your quant

Quant	Download	Memory	Estimated speed	Verdict
Q2_0 ★	7.2 GB	8.6 GB	~21.3–29.8 tok/s	✓ Runs great
Q2_g64	7.6 GB	9 GB	~20.2–28.3 tok/s	✓ Runs great

Get it running on this Mac

Choose the beginner-friendly build instead.

This Mac has enough memory, but the tracked Q2_0 ternary file is not supported by the current point-and-click apps. For a first local chat, use Bonsai 27B 1-bit in Locally AI. Do not download PQ2_0; the publisher marks it unsupported.

Only use the publisher tool if you are comfortable with Terminal.

The advanced path is complete below, but it is not required for ordinary local AI.

Advanced publisher setup (Terminal)

Install Apple's command-line tools if macOS asks, then run:

git clone https://github.com/PrismML-Eng/Bonsai-demo.git
cd Bonsai-demo
BONSAI_OPENWEBUI=0 BONSAI_SKIP_MLX=1 BONSAI_FAMILY=ternary BONSAI_MODEL=27B ./setup.sh
BONSAI_FAMILY=ternary BONSAI_MODEL=27B BONSAI_CTX=4096 ./scripts/start_llama_server.sh

When the server says it is ready, open http://localhost:8080. Start with 4K context. This route uses the publisher's Prism runtime, not Jan or LM Studio.

Other models on this Mac

Llama 3.3 70B · Q4_K_M Qwen 3.5 35B-A3B · Q4_K_M Qwen 3.6 35B-A3B · Q4_K_M Ornith 1.0 35B-A3B · Q4_K_M KAT-Coder V2.5 Dev · Q4_K_M Laguna XS 2.1 · Q4_K_M

Ternary Bonsai 27B on other MacBook Pro M5 Pro configurations

Check 24GB Check 48GB

FAQ

Can the MacBook Pro M5 Pro · 64GB run Ternary Bonsai 27B?

Yes at Q2_0. We estimate about 8.6GB of working memory and 21.3–29.8 tokens/s at 4K context.

Which Ternary Bonsai 27B quant should I use on this Mac?

Q2_0. It is a 7.2GB download and leaves about 49GB inside our conservative working budget.

Which app should I use for Ternary Bonsai 27B on this Mac?

Current beginner Mac apps do not load this exact file. Use Bonsai 27B 1-bit in Locally AI instead, or open the advanced publisher instructions on this page.

Are these speeds measured on a MacBook Pro M5 Pro?

No. The range is a formula estimate based on memory bandwidth, model size, active parameters, cooling, and a 4K context. The app, backend, thermals, and prompt can change real performance.