Gemma 4 31B

Oct 12, 2026

Throughput

21.4 t/s gen · 235.1 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

4bit MLX (MLX)

System RAM

512 GB

Use cases

long-context

Summary

User reports Gemma 4 31B at 21.4 t/s generation and 235.1 t/s prompt processing on a single Mac Studio with an M3 Ultra and 512 GB unified memory. Setup is mlx-vlm with 4bit MLX, 36,777 actual input tokens and 128 generated tokens per run, three runs, peak memory 29.7 GB. The figures are medians; prompt processing p10/p90 are 234.8 and 236.1 t/s, and KV quantization, flash attention and speculative decoding are not exposed.