Skip to content
localmodel.run

text model · Yi · macOS

Yi Can I run Yi 1.5 34B on Apple M3 Ultra (256GB)?

Compatibility verdict VRAM threshold engine
Yes, it runsusable speed

Yes. Yi 1.5 34B runs on Apple M3 Ultra (256GB) at Q4_K_M (~21.4 GB of ~192 GB usable).

Needs ~21.4 GB Device usable ~192 GB

Runs at Q4_K_M using ~21.4 GB of ~192 GB usable. You have room for FP16 for higher quality.

Q4_K_M needed
~21.4 GB
Usable on device
~192 GB
Device memory
256 GB
Best quant
Q4_K_M

Run it

Install commands macOS

Pick your tool. All three load the same Q4_K_M weights.

llama.cpp
$ llama-cli -hf bartowski/Yi-1.5-34B-Chat-GGUF:Q4_K_M
LM Studio
$ lms get bartowski/Yi-1.5-34B-Chat-GGUF

vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.

How to run it

On macOS use LM Studio (Polished GUI, ships MLX on Apple Silicon, one-click model downloads.). vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.

Model Yi
Parameters
34B
Q4_K_M size
19.24 GB
Q8_0 size
34.03 GB
Context
32k
Full Yi 1.5 34B requirements →
Device macOS
Memory
256 GB unified
Usable for weights
~192 GB
Best runtime
MLX direct / Ollama (MLX backend)
Best models for Apple M3 Ultra (256GB) →

You could also run

Run Yi 1.5 34B on other hardware

FAQ

Can Apple M3 Ultra (256GB) run Yi 1.5 34B?

Yes. Yi 1.5 34B runs on Apple M3 Ultra (256GB) at Q4_K_M (~21.4 GB of ~192 GB usable).

How much memory does Yi 1.5 34B need?

Apple M3 Ultra (256GB) has room to spare. At Q4_K_M the weights are ~19.24 GB; with KV cache and runtime overhead, budget ~21.4 GB at a 4k context.

What is the best tool to run Yi 1.5 34B on macOS?

LM Studio for a simple setup; mlx-lm for the most speed. vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.

Sources

Memory figures are estimates. See methodology.