Qwen3.5-27B on Apple M4 Max (36GB Unified)

M4 Max (36GB Unified) runs Qwen3.5-27B at Q8_0 — 16 tok/s. Usable on 36 GB VRAM — see full quantization options below.

Model Size

27B

Device VRAM

36 GB

Bandwidth

546 GB/s

Quantization

Q8_0

Benchmarks

Performance by Quantization

OwnRig currently has one published compatibility entry for Qwen3.5-27B on Apple M4 Max (36GB Unified) at Q8_0. This is the best supported pairing we can stand behind today.

Quantization	Speed	TTFT	Fits in VRAM	Rating	Confidence
Q8_0	16 tok/s	667ms	✓ Yes	Acceptable	estimated

Notes

Q8_0

Full quality Q8_0 with 8.4GB headroom. Silicon Score ranks the M4 Max 36GB class at 16.1 tok/s for this model on Apple Silicon.

About Qwen3.5-27B

Qwen3.5-27B (27B) is a chat, coding, ai coding, reasoning, multi-purpose model. Dense 27B from the Qwen 3.5 family. Native multimodal (text, image, video). 256K context window. Competitive with Gemma 3 27B and Qwen 3 32B at lower VRAM. Apache 2.0.

View all Qwen3.5-27B 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: Machine-specific Apple Silicon estimate for M4 Max 36GB at 8bit / llama.cpp. Reference hardware source: siliconscore.com (2026-04-11)

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.