Can Ternary Bonsai 8B run on MacBook Neo A18 Pro 8GB?

YES — Runs, barely

Q2_0 · 4K context · formula estimate

What this means

Ternary Bonsai 8B fits on the MacBook Neo A18 Pro · 8GB at Q2_0. We estimate it uses 3.7GB of the conservative 5GB working budget.

Estimated decode speed is 11.5–15.8 tokens/s. A roughly 300-word answer may take around 29 seconds.

View technical details ↓Setup guide →

11.5–15.8tokens/s

estimated · faster than you read

3.7GB

needed at Q2_0

Q2_0

quant selected

1.3GB

working headroom

needs 3.7 GBworking budget 5 GB

Apple A18 Pro8 GB unified memoryMetalFanless

See how fast it feels

Using the midpoint of our 11.5–15.8 tokens/s estimate for this demo.

Live demo · 13.7 tokens/s

▌

Compare other speeds →

Where the memory goes

Component	Detail	GB
Model weights	Q2_0 GGUF (2.2 GB) + mmap overhead	2.3
KV cache	4K context window	0.6
Runtime	macOS inference app + compute buffers	0.8
Total needed	Q2_0, 4K context	3.7
Working budget	8 GB unified memory − conservative macOS reserve	5
Headroom	remaining inside the working budget	1.3

Pick your quant

Quant	Download	Memory	Estimated speed	Verdict
Q2_0 ★	2.2 GB	3.7 GB	~11.5–15.8 tok/s	! Runs, barely
Q2_0_g64	2.3 GB	3.8 GB	~11–15.1 tok/s	! Runs, barely

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=8B ./setup.sh
BONSAI_FAMILY=ternary BONSAI_MODEL=8B 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

Ternary Bonsai 4B · Q2_0 Llama 3.2 3B · Q4_K_M SmolLM3 3B · Q4_K_M Ministral 3 3B · Q4_K_M G9v3 3B · Q4_K_M Qwen 3.5 2B · Q4_K_M

FAQ

Can the MacBook Neo A18 Pro · 8GB run Ternary Bonsai 8B?

Yes at Q2_0. We estimate about 3.7GB of working memory and 11.5–15.8 tokens/s at 4K context.

Which Ternary Bonsai 8B quant should I use on this Mac?

Q2_0. It is a 2.2GB download and leaves about 1.3GB inside our conservative working budget.

Which app should I use for Ternary Bonsai 8B 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 Neo A18 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.