Can Ternary Bonsai 1.7B run on MacBook Pro M3 Max 128GB?

YES — Runs great

Q2_0 · 4K context · formula estimate

What this means

Ternary Bonsai 1.7B fits on the MacBook Pro M3 Max · 128GB at Q2_0. We estimate it uses 1.4GB of the conservative 120GB working budget.

Estimated decode speed is 400–560 tokens/s. A roughly 300-word answer may take around 1 seconds.

View technical details ↓Setup guide →

400–560tokens/s

estimated · instant

1.4GB

needed at Q2_0

Q2_0

quant selected

118.6GB

working headroom

needs 1.4 GBworking budget 120 GB

Apple M3 Max (40-core GPU)128 GB unified memoryMetalActive cooling

See how fast it feels

Using the midpoint of our 400–560 tokens/s estimate for this demo.

Live demo · 480 tokens/s

▌

Compare other speeds →

Where the memory goes

Component	Detail	GB
Model weights	Q2_0 GGUF (0.5 GB) + mmap overhead	0.5
KV cache	4K context window	0.1
Runtime	macOS inference app + compute buffers	0.8
Total needed	Q2_0, 4K context	1.4
Working budget	128 GB unified memory − conservative macOS reserve	120
Headroom	remaining inside the working budget	118.6

Pick your quant

Quant	Download	Memory	Estimated speed	Verdict
Q2_0 ★	0.5 GB	1.4 GB	~400–560 tok/s	✓ Runs great
Q2_0_g64	0.5 GB	1.4 GB	~400–560 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=1.7B ./setup.sh
BONSAI_FAMILY=ternary BONSAI_MODEL=1.7B 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

Hunyuan 3 (Hy3) · IQ1_S Laguna S 2.1 · Q4_K_M 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

Ternary Bonsai 1.7B on other MacBook Pro M3 Max configurations

Check 36GB Check 64GB

FAQ

Can the MacBook Pro M3 Max · 128GB run Ternary Bonsai 1.7B?

Yes at Q2_0. We estimate about 1.4GB of working memory and 400–560 tokens/s at 4K context.

Which Ternary Bonsai 1.7B quant should I use on this Mac?

Q2_0. It is a 0.5GB download and leaves about 118.6GB inside our conservative working budget.

Which app should I use for Ternary Bonsai 1.7B 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 M3 Max?

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.