← All benchmarks

SiliconBench › Chips › M4 Max (128 GB)

M4 Max (128 GB) — LLM Benchmarks

Measured LLM inference benchmarks for M4 Max (128 GB). Tokens per second across 7 models and multiple quantizations. Real runs, not estimates.

7 Benchmark rows
7 Models tested
184.4 Fastest avg tok/s (Qwen 3 0.6B)
0 Factory-lab verified rows

Benchmark results for M4 Max (128 GB)

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

Model Quant RAM req. Context Avg tok/s Prompt tok/s Runtime Source
Qwen 3 0.6B Q8_0 — 10k 184.4 tok/s — LM Studio ref
Gemma 3 4B Q4_0 — 4k 100.5 tok/s — LM Studio ref
Qwen 3 30B A3B Q4_K_M — 10k 70.2 tok/s — LM Studio ref
Qwen 3 8B Q4_K_M — 10k 63.1 tok/s — LM Studio ref
Qwen 2.5 7B Instruct Q8_0 — 10k 49.7 tok/s — LM Studio ref
Gemma 3 27B Q8_0 — 131k 14.5 tok/s — LM Studio ref
Qwen 3 235B A22B Q4_K_M — 10k 8.1 tok/s — LM Studio ref

Models tested on this chip

Gemma 3 4B Gemma 3 27B Qwen 2.5 7B Instruct Qwen 3 0.6B Qwen 3 8B Qwen 3 30B A3B Qwen 3 235B A22B

Data

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

Want to contribute a benchmark for this chip? Data sourced from factory lab measurements and community reference runs. See all chips →