Gemma 4 8B E4B

Oct 13, 2026

Throughput

46.2 t/s gen · 770.2 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

Q8_0 (GGUF)

KV cache

F16

System RAM

64 GB

Summary

User reports Gemma 4 E4B at 46.2 t/s generation and 770.2 t/s prompt processing on an M4 Pro 64GB. Setup is dasLLAMA with Q8_0 weights, f16 KV cache, and one Metal GPU, with 640 positions allocated. The figures are native PP512 and TG128 counts, not one 512-input/128-output request, and no longer-context performance is inferred.