Prefill and token generation speed
RTX 3090 24GB with Gemma 4 12B: prefill and generation speed
Last updated
936 GB/s
11.95B
95.5 ~ 106.1 tok/sDecode speed
Model fully loaded (8GB / 22.5GB)
First token (TTFT)
2.2 to 3.8 secondsContext 4,096 input tokens included
Prefill speed
1,069 ~ 1,842 tok/s2.2 to 3.8 seconds (Estimation based on public benchmarks)
Total time (E2E)
Approximately 3.3 to 5.1 seconds117 output tokens included
Press Play to process the input and generate the answer.
Ready
Expand settings Settings4-bit · 4K · Baseline decodeCollapse
QuantizationNeed 8GB
Input context4K tokens
Baseline
Baseline
Sample question:
117 output tokensCheck configuration
RTX 3090 24GB · Memory 24GB
Gemma 4 12B Q4_K_M configuration. Check that the retailer lists the same memory option.
Already own it? Open the setup guideWould another device feel faster?
Compare the same model including prefill, or just token generation.
What changes with a longer document?Expand input length, waiting time, speed and memory
Detailed analysis and all 60 hardware configurations
Popular configurations
Speed simulations by device and model
Gemma 4 12B on Mac mini M4 24GB: chat speed
11.6 ~ 12.9 tok/s · 12.8 ~ 31.1 s
Qwen3.8 27B on RTX 3090: do you need an upgrade?
42.3 ~ 46.9 tok/s · 4.4 to 7.5 seconds
Qwen3.8 27B on Mac mini M4 32GB: response speed
5.1 ~ 5.7 tok/s · 16.4 ~ 35.5 s
Qwen3.8 27B: is a Mac mini M4 Pro 48GB worth it?
12.3 ~ 13.7 tok/s · 7.8 ~ 14.3 s