Google Gemma 4 31B

Q4_0 running on Apple M1 Max with macOS 27.0

PERFORMANCE / TOKENS PER SECONDApple Silicon

Prompt processing101.03tok/s

#322 in index

Token generation14.91tok/s

#273 in index

Run fingerprint

Enough context to make the number useful.

ModelGoogle Gemma 4 31BDense architecture

QuantizationQ4_0Exact submitted variant

GPUApple M1 Max51.84 GB VRAM

GPU architectureApple SiliconMetal backend

Test context512prompt tokens

Model familyDenseSigned ToshLLM app · amd-gpu · Metal

ToshLLM versionv0.87.7App version used to capture and sign this run

Prompt processing and generation are reported separately so memory bandwidth and decode behavior stay visible.

Quantization, GPU family, VRAM and context travel with the result instead of being hidden behind one score.

This result remains explicitly labeled as a community submission.