Silicon Score
← All benchmarks

Silicon Score › Chips › M2 (10-core GPU)

M2 (10-core GPU) — LLM Benchmarks

Measured LLM inference benchmarks for M2 (10-core GPU) across all RAM configurations (8 GB, 16 GB, 24 GB). 7 benchmark rows across 3 models. Compare how RAM affects throughput. Real runs, not estimates.

7Benchmark rows
3Models tested
3RAM configurations
56.5Fastest avg tok/s

RAM configurations

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

8 GBM2 (10-core GPU, 8 GB)1 rows · 1 models56.5 tok/s peak16 GBM2 (10-core GPU, 16 GB)3 rows · 3 models55.6 tok/s peak24 GBM2 (10-core GPU, 24 GB)3 rows · 3 models54.8 tok/s peak

All benchmark rows — M2 (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
M2 (10-core GPU, 8 GB)Llama 3.2 1B InstructQ4_K - Medium—56.5 tok/s804.8 tok/s—ref
M2 (10-core GPU, 16 GB)Llama 3.2 1B InstructQ4_K - Medium—55.6 tok/s801.8 tok/s—ref
M2 (10-core GPU, 24 GB)Llama 3.2 1B InstructQ4_K - Medium—54.8 tok/s813.7 tok/s—ref
M2 (10-core GPU, 16 GB)Llama 3.1 8B InstructQ4_K - Medium—14.7 tok/s140.7 tok/s—ref
M2 (10-core GPU, 24 GB)Llama 3.1 8B InstructQ4_K - Medium—14.7 tok/s141.7 tok/s—ref
M2 (10-core GPU, 16 GB)Qwen 2.5 14B InstructQ4_K - Medium—8.1 tok/s74.8 tok/s—ref
M2 (10-core GPU, 24 GB)Qwen 2.5 14B InstructQ4_K - Medium—7.3 tok/s70.3 tok/s—ref

Models tested on M2 (10-core GPU)

Llama 3.1 8B InstructLlama 3.2 1B InstructQwen 2.5 14B Instruct

Data

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 →