Silicon Score
← All benchmarks

Silicon Score › Chips › M4 (8-core GPU, 16 GB)

M4 (8-core GPU, 16 GB) — LLM Benchmarks

Measured LLM inference benchmarks for M4 (8-core GPU, 16 GB). Tokens per second across 3 models and multiple quantizations. Real runs, not estimates.

3Benchmark rows
3Models tested
65.9Fastest avg tok/s (Llama 3.2 1B Instruct)
0Factory-lab verified rows

Benchmark results for M4 (8-core GPU, 16 GB)

Rows sorted by avg tok/s descending. Click source badge to see original measurement page.

ModelQuantRAM req.ContextAvg tok/sPrompt tok/sRuntimeSource
Llama 3.2 1B InstructQ4_K - Medium——65.9 tok/s897.0 tok/s—ref
Llama 3.1 8B InstructQ4_K - Medium——15.3 tok/s134.0 tok/s—ref
Qwen 2.5 14B InstructQ4_K - Medium——7.2 tok/s61.1 tok/s—ref

Models tested on this chip

Llama 3.2 1B InstructLlama 3.1 8B 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 →