Is the M5 Pro faster than the M4 Pro for LLMs?

The M5 Pro reads memory about 12% faster than the M4 Pro (307 vs 273 GB/s), so it writes about 12% faster with any model that fits both. Reading a long prompt depends on GPU compute instead, which this comparison doesn’t cover.

Which can run bigger models, the M4 Pro or the M5 Pro?

Neither: both go up to 64 GB. At that size the M4 Pro runs 31 and the M5 Pro 34 of 73 open models well; the faster one clears more of them at 10 tokens a second.

M4 Pro vs M5 Pro for local LLMs: memory, speed, which to buy

Side by side

	M4 Pro	M5 Pro
Memory sizes	24, 48, 64 GB	24, 48, 64 GB
Memory bandwidth	273 GB/s	307 GB/s
For models, at most	about 48 GB	about 48 GB
Models that run well	31 of 73	34 of 73
MLX seat class	Pro	Pro Latest
Found in	Mac mini (2024), MacBook Pro (14-inch, M4 Pro or M4 Max, 2024), MacBook Pro (16-inch, 2024)	MacBook Pro (14-inch, M5 Pro or M5 Max), MacBook Pro (16-inch, M5 Pro or M5 Max), Mac mini (M6 or M5 Pro)

Speed with popular models

Tokens a second for one conversation, each chip at its largest memory size (64 GB and 64 GB), with the best version of the model that fits.

Model	M4 Pro	M5 Pro
Llama 3.1 8B Instruct8B	14–26 8-bit	16–29 8-bit
gpt-oss-20b21B · 3.6B active	65–115 native 4.25-bit	73–129 native 4.25-bit
Qwen3.6 35B A3B35B · 3B active	38–68 8-bit	43–77 8-bit
Qwen3.8 27B27B	4–8 8-bit	5–9 8-bit
Llama 3.3 70B Instruct70B	3–6 4-bit	4–6 4-bit
gpt-oss-120b117B · 5.1B active	77–137 2-bit lower quality	86–154 2-bit lower quality
Qwen3.5 122B A10B122B · 10B active	40–70 2-bit lower quality	45–79 2-bit lower quality
DeepSeek V4 Flash 0731284B · 13B active	too big	too big

Questions

Is the M5 Pro faster than the M4 Pro for LLMs?: The M5 Pro reads memory about 12% faster than the M4 Pro (307 vs 273 GB/s), so it writes about 12% faster with any model that fits both. Reading a long prompt depends on GPU compute instead, which this comparison doesn’t cover.
Which can run bigger models, the M4 Pro or the M5 Pro?: Neither: both go up to 64 GB. At that size the M4 Pro runs 31 and the M5 Pro 34 of 73 open models well; the faster one clears more of them at 10 tokens a second.

More comparisons

The M4 Pro for local AI · The M5 Pro for local AI · Compare every model · The best Mac for local LLMs

How it’s worked out

Memory: the model’s parameters at 8, 6, 4, 3 or 2 bits per weight plus MLX’s group scales (half a bit per weight), or its native format, with room for the context on top. By default macOS lets the GPU use about 75% of unified memory. Speed: memory bandwidth divided by the bytes read per token is the ceiling for one conversation; in llama.cpp’s public Apple Silicon benchmarks real runs reach about 45% to 80% of it, which is the range shown. These are estimates, not measurements: measure your own Mac on MLX Bench. Model figures from each official model card, chip figures from Apple’s Tech Specs. Checked 2026-10-19. Same data as mlx.app/compare.