llamaperf

Gemma 2

2 reports

Gemma 2 VRAM requirements by size and quant →

How does Gemma 2 run on your hardware?

Pick your GPU or Mac, then read the speeds people reported for Gemma 2 on it, or estimate memory fit and speed.

Free to use. No account needed. Memory estimates and community measurements are labelled separately.

Run Gemma 2 yourself? Add your numbers.

Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.

Reported performance for Gemma 2

Filter this model’s reports by setup →
2 reports for this model so far, so treat the figures as early. Add yours.

Speeds are as each source reported them. GPU count, offloading and concurrent requests change them, and prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing two reports.

Gemma 2 2B

Unknown GPU · PULSAR-ASM

generation:
4.5-4.7 tokens/s
quant:
FP16

User reports Gemma-2B at 4.5-4.7 tokens/s in FP16 on an older quad-core i5 desktop, CPU only. Setup is a custom 5.2 KB x86-64 assembly engine (PULSAR-ASM) using AVX2 and F16C with a 4-thread SMP GEMM for prefill, sustaining about 18.5 GB/s memory bandwidth on DDR4-2400. The engine has zero C/C++ runtime and zero PyTorch dependencies; the Python harness only uses ctypes for VirtualAlloc and OS threads.

Oct 4, 2026

Gemma 2 9B

Unknown GPU

Tone: positive
generation:
8.2 tokens/s

User reports Gemma 9B at 8.2 t/s sustained on a Snapdragon 8 Gen 5 phone, running purely on the CPU with an ~8GB memory footprint. Setup is a custom engine with ARM-specific optimizations, chosen over mobile OpenCL/Vulkan drivers, plus an ONNX-based Kokoro TTS voice engine running natively on-device. The run is fully offline and air-gapped with zero API calls.

Oct 3, 2026

Get a weekly email of new Gemma 2 reports on any GPU.

Email me new reports