Can I Run Yi 1.5 Family on MacBook Pro 16" (M4 Max, 48 GB)?

Newer alternative. 01.AI has not released a newer model in this library. If you are choosing today, Qwen 3 is a comparable current option. View Qwen 3 →

Written by Jakub Rusinowski · Last updated May 13, 2024

Yes

Yes — Yi 1.5 34B Chat at Q6_K needs about 31 GB of the 36 GB usable on MacBook Pro 16" (M4 Max, 48 GB) (~5 GB spare), at ~9.9 tok/s (estimated), with room for about 16,384 tokens of context.

Confidence: high · Recommended quantization: Q6_K · Estimated speed: ~9.9 tok/s

MacBook Pro 16" (M4 Max, 48 GB) — what it gives a model

Usable memory for models	36 GB
Memory bandwidth	546 GB/s
Form factor	Laptop
Operating system	macOS
Memory upgradeable	No — soldered
Price	$3,999 (lib/data/laptops.ts (street price), checked 2026-07-06)

Yi 1.5 Family on MacBook Pro 16" (M4 Max, 48 GB): memory by quantization

Quant	Memory needed	Fits 36 GB?	Max context	Est. speed	Download
F16	71.6 GB	✗ No	—	—	68.8 GB
Q8_0	39.4 GB	✗ No	—	—	36.6 GB
Q6_K	31 GB	✓ Yes	16K	~9.9 tok/s	28.2 GB
Q5_K_M	27.2 GB	✓ Yes	16K	~11.4 tok/s	24.4 GB
Q4_K_M	23.6 GB	✓ Yes	16K	~13.2 tok/s	20.8 GB
Q3_K_M	17.5 GB	✓ Yes	16K	~18.1 tok/s	14.7 GB
Q2_K	14.1 GB	✓ Yes	16K	~22.6 tok/s	11.3 GB

Which Yi 1.5 Family sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Yi 1.5 34B Chat	23.6 GB	✓ Fits	~13.2 tok/s
Yi 1.5 9B Chat	6.9 GB	✓ Fits	~45.1 tok/s

What to watch out for

Memory on this machine is not upgradeable, so the configuration you buy is the ceiling for every model you will ever run on it.

MacBook Pro M4 Max 48 GB limitations

Unified memory is soldered and cannot be upgraded after purchase.
macOS reserves a share of unified memory for the system, so not all 48 GB is available to a model.

Recommended setup

Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput

How these numbers are calculated

Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
48 GB unified memory at 546 GB/s, shared between CPU and GPU.
macOS reserves a share of unified memory for the system, so not all of it is available to a model.
Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
KV cache is computed from this model's published attention configuration.

FAQ