Code Llama 34B Instruct on Apple M4 Max (36GB Unified)

Yes — M4 Max (36GB Unified) handles Code Llama 34B Instruct well at Q4_K_M — 14 tok/s. Solid daily-driver performance on 36 GB VRAM.

Model Size

33.7B

Device VRAM

36 GB

Bandwidth

546 GB/s

Quantization

Q4_K_M

Benchmarks

Performance by Quantization

OwnRig currently has one published compatibility entry for Code Llama 34B Instruct on Apple M4 Max (36GB Unified) at Q4_K_M. This is the best supported pairing we can stand behind today.

Quantization	Speed	TTFT	Fits in VRAM	Rating	Confidence
Q4_K_M	14 tok/s	600ms	✓ Yes	Good	estimated

Notes

Q4_K_M

Q4 at 19GB in 36GB unified memory. 17GB headroom.

About Code Llama 34B Instruct

Code Llama 34B Instruct (33.7B) is a coding, ai coding model. Meta's dedicated 34B coding model. Still competitive for code generation but being surpassed by newer models like Qwen 2.5 Coder 32B. Shorter context window (16K) is a limitation for large codebases.

View all Code Llama 34B Instruct hardware options →

About Apple M4 Max (36GB Unified)

Apple M4 Max (36GB Unified) has 36 GB at 546 GB/s. Available in MacBook Pro 16", Mac Studio.

See all models Apple M4 Max (36GB 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.