RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Yi 1.5 34B Chat run on the Mac M3 Max 128GB?

Yes. At 8K context the best fit is F16, using about 66.5 GB of the 96.0 GB usable on the Mac M3 Max 128GB. Estimated speed ceiling: ~6 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •13.4 GB Fits31
3-bit (Q3_K_M)17.1 GB Fits24
4-bit (Q4_K_M) •20.7 GB Fits19
5-bit (Q5_K_M) •24.1 GB Fits16
6-bit (Q6_K) •27.7 GB Fits14
8-bit (Q8_0) •35.5 GB Fits11
16-bit (F16/BF16)65.5 GB Fits6

• real GGUF file size from lmstudio-community/Yi-1.5-34B-Chat-GGUF. Speed is a bandwidth ceiling (400 GB/s), not a benchmark. Methodology.

More

Yi 1.5 34B Chat on every GPU and Mac · Every model that runs on the Mac M3 Max 128GB · Apple Silicon guide · Try other settings in the calculator

Data: Hugging Face Hub (01-ai/Yi-1.5-34B-Chat), Apple specs. Data as of 2026-11-17.