Qwen 2.5 Coder 32B Instruct on Apple M4 Max (64GB Unified)

Yes — M4 Max (64GB Unified) handles Qwen 2.5 Coder 32B Instruct well at Q5_K_M — 18 tok/s. Solid daily-driver performance on 64 GB VRAM.

Model Size

32.5B

Device VRAM

64 GB

Bandwidth

546 GB/s

Quantization

Q5_K_M

Benchmarks

Performance by Quantization

OwnRig currently has one published compatibility entry for Qwen 2.5 Coder 32B Instruct on Apple M4 Max (64GB Unified) at Q5_K_M. This is the best supported pairing we can stand behind today.

Quantization	Speed	TTFT	Fits in VRAM	Rating	Confidence
Q5_K_M	18 tok/s	500ms	✓ Yes	Good	estimated

Notes

Q5_K_M

Same speed as 36GB M4 Max. The extra memory enables the full concurrent builder workflow on a Mac.

64GB allows running Qwen Coder 32B Q5 (22GB) + Llama 8B Q4 (5GB) + nomic-embed (0.5GB) = ~27.5GB concurrent, leaving 36.5GB free for system.

About Qwen 2.5 Coder 32B Instruct

Qwen 2.5 Coder 32B Instruct (32.5B) is a coding, ai coding, ai building model. The coding model that defines the builder workflow. Matches GPT-4 on HumanEval. This is what Cursor and Continue.dev users run locally when they want to eliminate API dependency. Apache 2.0 license. The cornerstone of the 'Full AI Builder' profile.

View all Qwen 2.5 Coder 32B Instruct hardware options →

About Apple M4 Max (64GB Unified)

Apple M4 Max (64GB Unified) has 64 GB at 546 GB/s. Available in MacBook Pro 16", Mac Studio.

See all models Apple M4 Max (64GB Unified) can run →

Estimate method: MLX performance estimates. Reference hardware source: github.com (2026-01-15)

Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.