← All benchmarks

M4 (10-core GPU) — LLM Benchmarks

Measured LLM inference benchmarks for M4 (10-core GPU) across all RAM configurations (16 GB, 24 GB, 32 GB). 10 benchmark rows across 4 models. Compare how RAM affects throughput. Real runs, not estimates.

10Benchmark rows
4Models tested
3RAM configurations
76.2Fastest avg tok/s

Each configuration differs only in unified memory. More RAM = larger models fit. Throughput is similar across RAM tiers at the same model size.

All benchmark rows — M4 (10-core GPU)

Sorted by avg tok/s descending. Click source badge to see original measurement.

Chip (RAM)ModelQuantRAM req.Avg tok/sPrompt tok/sRuntimeSource
M4 (10-core GPU, 16 GB)Llama 3.2 1B InstructQ4_K - Medium76.2 tok/s1091.1 tok/sref
M4 (10-core GPU, 32 GB)Llama 3.2 1B InstructQ4_K - Medium75.6 tok/s1069.9 tok/sref
M4 (10-core GPU, 24 GB)Llama 3.2 1B InstructQ4_K - Medium75.4 tok/s1036.0 tok/sref
M4 (10-core GPU, 16 GB)Llama 2 7BQ4_03.6 GB24.1 tok/s221.3 tok/sllama.cppref
M4 (10-core GPU, 32 GB)Llama 3.1 8B InstructQ4_K - Medium16.8 tok/s166.1 tok/sref
M4 (10-core GPU, 16 GB)Llama 3.1 8B InstructQ4_K - Medium16.0 tok/s166.8 tok/sref
M4 (10-core GPU, 24 GB)Llama 3.1 8B InstructQ4_K - Medium15.9 tok/s149.0 tok/sref
M4 (10-core GPU, 24 GB)Qwen 2.5 14B InstructQ4_K - Medium9.2 tok/s93.3 tok/sref
M4 (10-core GPU, 16 GB)Qwen 2.5 14B InstructQ4_K - Medium8.7 tok/s83.1 tok/sref
M4 (10-core GPU, 32 GB)Qwen 2.5 14B InstructQ4_K - Medium8.6 tok/s79.3 tok/sref

benchmarks.json — full dataset  ·  chips.json — chip summaries  ·  benchmarks.csv — CSV export

Data sourced from factory lab measurements and community reference runs. See all chips →