Can the M5 Pro run a 70B model?

Yes. A 70B model at 4-bit needs about 40 GB, and the M5 Pro has up to 64 GB. Expect a ceiling of about 8 tokens a second for one chat.

How many tokens per second does the M5 Pro get?

For an 8B model at 4-bit, the ceiling is about 68 tokens a second, and real runs reach roughly half to four fifths of it. Bigger models are proportionally slower.

Is the M5 Pro good for AI?

For running models locally, memory and bandwidth matter most. The M5 Pro has up to 64 GB at 307 GB/s, enough for models up to about 85 billion parameters. It can also earn by running AI work for MLX Network with MLX Node.

M5 Pro for local LLMs: memory, speed and what fits

1The specs that matter for AI

Unified memory	64 GB
Memory bandwidth	307 GB/s
Found in	14- and 16-inch MacBook Pro (2026), Mac mini (2026)
Dedicated seat for it	Pro Latest seat: mines up to 120 MLX a day

2Which models fit

At 4 bits per weight a model needs a little over half a gigabyte per billion parameters, plus room for its context and macOS. With 64 GB, the M5 Pro comfortably holds models up to about 85 billion parameters.

Model at 4-bit	Memory it needs	Fits on the M5 Pro
8B model	4.5 GB	Yes
14B model	7.9 GB	Yes
32B model	18 GB	Yes
70B model	39.4 GB	Yes
gpt-oss-120b, mixture-of-experts	65 GB	No
Qwen3.5-397B-A17B, mixture-of-experts	223.3 GB	No
DeepSeek-V4.1-Flash, mixture-of-experts	316 GB	No

3How fast it runs

Writing text is limited by memory bandwidth: every new token reads the model's active weights once. Dividing the M5 Pro's 307 GB/s by the bytes read per token gives the ceiling below. Real runs usually reach about 45% to 80% of it (llama.cpp benchmarks).

Model at 4-bit	Read per token	Ceiling for one chat
8B model	4.5 GB	68 tokens/s
14B model	7.9 GB	39 tokens/s
32B model	18 GB	17 tokens/s
70B model	39.4 GB	8 tokens/s

M5-generation chips add neural accelerators to the GPU, so they read prompts several times faster than M4: Apple measured the first token arriving 3.3 to 4.1 times sooner with MLX (Apple).

5Compare with other chips

6Questions

Can the M5 Pro run a 70B model?: Yes. A 70B model at 4-bit needs about 40 GB, and the M5 Pro has up to 64 GB. Expect a ceiling of about 8 tokens a second for one chat.
How many tokens per second does the M5 Pro get?: For an 8B model at 4-bit, the ceiling is about 68 tokens a second, and real runs reach roughly half to four fifths of it. Bigger models are proportionally slower.
Is the M5 Pro good for AI?: For running models locally, memory and bandwidth matter most. The M5 Pro has up to 64 GB at 307 GB/s, enough for models up to about 85 billion parameters. It can also earn by running AI work for MLX Network with MLX Node.

Sources

Apple: M5 Pro and M5 Maxapple.com
Apple: Mac mini (2026) specssupport.apple.com