RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen2.5 Coder 14B Instruct run on the Mac M4 Max 128GB?

Yes. At 8K context the best fit is F16, using about 29.7 GB of the 96.0 GB usable on the Mac M4 Max 128GB. Estimated speed ceiling: ~18 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)6.6 GB Fits7.3 GB Fits11.8 GB Fits99
3-bit (Q3_K_M)8.2 GB Fits8.9 GB Fits13.4 GB Fits76
4-bit (Q4_K_M)9.8 GB Fits10.6 GB Fits15.1 GB Fits60
5-bit (Q5_K_M)11.2 GB Fits12.0 GB Fits16.5 GB Fits52
6-bit (Q6_K)12.7 GB Fits13.5 GB Fits18.0 GB Fits45
8-bit (Q8_0)16.1 GB Fits16.8 GB Fits21.3 GB Fits35
16-bit (F16/BF16)29.0 GB Fits29.7 GB Fits34.2 GB Fits18

• real GGUF file size. Speed is a bandwidth ceiling (546 GB/s), not a benchmark. Methodology.

More

Qwen2.5 Coder 14B Instruct on every GPU and Mac · Every model that runs on the Mac M4 Max 128GB · Apple Silicon guide · Try other settings in the calculator

Data: Hugging Face Hub (Qwen/Qwen2.5-Coder-14B-Instruct), Apple specs. Data as of 2026-11-17.