Speed test matrix
granite-4.2-3b-fp8 on RTX 3060 12GB
vllm · 0.32.0 · FP84 contexts (0–64K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 64K
Hardware
- Type
- Discrete GPU
- GPU
- RTX 3060
- VRAM
- 12 GB
- CPU
- Intel Xeon E5-2680 v4 (14C)
- RAM
- 32 GB
- OS
- Ubuntu 24.04.5
Engine
- Engine
- vllm
- Version
- 0.32.0
- Quantization
- FP8
- Backend
- cuda
- Repository
- github.com/vllm-project/vllm
- Build
- vllm/vllm-openai:v0.32.0-x86_64
Run
- Served model
- bench
- Revision
- main
- Benchmark tool
- llm-inference-bench v0.8.0
- Decode test
- Fixed duration
- Prefill mode
- Measured during decode warm-up
- Time per measurement
- 30 s
- Max output
- 8,192 tokens
Launch command
# Untuned out-of-the-box baseline. Spec decode: none # 1x RTX 3060 12GB, stock 170 W limit, PCIe Gen3 x16 | Intel Xeon E5-2680 v4 14C | 32 GB DDR4-2400 | Ubuntu 24.04.5, NVIDIA driver 580.178.04 vllm serve ibm-granite/granite-4.2-3b-fp8 --max-model-len 73728 --gpu-memory-utilization 0.94 --max-num-seqs 128 --enable-prefix-caching --trust-remote-code
Prefill
prompt tok/s by context length8K context2,8412,886 ms TTFT
16K context2,2947,068 ms TTFT
32K context1,69519,039 ms TTFT
64K context1,10558,254 ms TTFT
Sustained decode
total tok/s · rows are context length, columns are simultaneous requests| Context | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128 |
|---|---|---|---|---|---|---|---|---|
| 0 | 74.556 ms TTFT | 141.665 ms TTFT | 263.055 ms TTFT | 478.074 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 16K | 54.7152 ms TTFT | 86.1230 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 43.2255 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 64K | 30.2504 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
Over capacity: not run because this many requests at this context would exceed the server's KV cache.
TTFT is measured after the benchmark warms the server's prompt cache, so it mostly excludes prefill.
All measurements
Latencies are medians. Total tok/s is output across all simultaneous requests.| Phase | Context | Requests at once | Status | Total tok/s | Per request tok/s | TTFT | Time between tokens | Average active requests | Completed requests | Output tokens | Measured for |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Prefill | 8K | 1 | Valid | 2,841.0 | — | 2,886 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 2,294.0 | — | 7,068 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 1,695.0 | — | 19,039 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 1,105.0 | — | 58,254 ms | — | — | 1 | — | — |
| Sustained decode | 0 | 1 | Valid | 74.5 | 75.1 | 56 ms | 13.3 ms | 1.0 | 0 | 2,234 | 30.0 s |
| Sustained decode | 0 | 2 | Valid | 141.6 | 71.6 | 65 ms | 14.0 ms | 2.0 | 0 | 4,247 | 30.0 s |
| Sustained decode | 0 | 4 | Valid | 263.0 | 67.0 | 55 ms | 14.9 ms | 4.0 | 0 | 7,887 | 30.0 s |
| Sustained decode | 0 | 8 | Valid | 478.0 | 61.8 | 74 ms | 16.2 ms | 8.0 | 0 | 14,336 | 30.0 s |
| Sustained decode | 0 | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 1 | Valid | 54.7 | 54.8 | 152 ms | 18.2 ms | 1.0 | 0 | 1,640 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 86.1 | 43.1 | 230 ms | 23.2 ms | 2.0 | 0 | 2,582 | 30.0 s |
| Sustained decode | 16K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 1 | Valid | 43.2 | 43.3 | 255 ms | 23.1 ms | 1.0 | 0 | 1,297 | 30.0 s |
| Sustained decode | 32K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 1 | Valid | 30.2 | 30.4 | 504 ms | 32.9 ms | 1.0 | 0 | 907 | 30.0 s |
| Sustained decode | 64K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Over capacity: not run because this many requests at this context would exceed the server's KV cache.