Speed test matrix
granite-4.2-3b-fp8 on RTX 3060 12GB
vllm · 0.32.0 · FP85 contexts (0–120K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 64K, 120K
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. KV cache: fp8 # 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 131072 --gpu-memory-utilization 0.94 --max-num-seqs 128 --enable-prefix-caching --trust-remote-code --kv-cache-dtype fp8
Prefill
prompt tok/s by context length8K context138.059,495 ms TTFT
16K context2,2987,055 ms TTFT
32K context1,69319,058 ms TTFT
64K context1,09159,021 ms TTFT
120K context672.0179,468 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 | 76.431 ms TTFT | 146.462 ms TTFT | Failed | Failed | Failed | Over capacity | Over capacity | Over capacity |
| 16K | 64.5172 ms TTFT | Failed | Failed | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 55.7260 ms TTFT | Failed | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 64K | 43.6431 ms TTFT | Failed | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 120K | 31.7Requests queued656 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
Requests queued: the server could not run all requests at once, so some waited in a queue. Failed: requests to the server failed during this measurement. 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 | 138.0 | — | 59,495 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 2,298.0 | — | 7,055 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 1,693.0 | — | 19,058 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 1,091.0 | — | 59,021 ms | — | — | 1 | — | — |
| Prefill | 120K | 1 | Valid | 672.0 | — | 179,468 ms | — | — | 1 | — | — |
| Sustained decode | 0 | 1 | Valid | 76.4 | 76.6 | 31 ms | 13.0 ms | 1.0 | 0 | 2,292 | 30.0 s |
| Sustained decode | 0 | 2 | Valid | 146.4 | 68.3 | 62 ms | 14.6 ms | 3.0 | 0 | 4,392 | 30.0 s |
| Sustained decode | 0 | 4 | Failed | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 0 | 8 | Failed | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 0 | 16 | Failed | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 0 | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 1 | Valid | 64.5 | 64.6 | 172 ms | 15.5 ms | 1.0 | 0 | 1,934 | 30.0 s |
| Sustained decode | 16K | 2 | Failed | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 4 | Failed | — | — | — | — | — | 0 | 0 | — |
| 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 | 55.7 | 55.8 | 260 ms | 17.9 ms | 1.0 | 0 | 1,670 | 30.0 s |
| Sustained decode | 32K | 2 | Failed | — | — | — | — | — | 0 | 0 | — |
| 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 | 43.6 | 43.7 | 431 ms | 22.9 ms | 1.0 | 0 | 1,307 | 30.0 s |
| Sustained decode | 64K | 2 | Failed | — | — | — | — | — | 0 | 0 | — |
| 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 | — | — | — | — | — | — | — | — |
| Sustained decode | 120K | 1 | Requests queued | 31.7 | 31.8 | 656 ms | 31.4 ms | 1.0 | 0 | 951 | 30.0 s |
| Sustained decode | 120K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 120K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 120K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 120K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 120K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 120K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 120K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Requests queued: the server could not run all requests at once, so some waited in a queue. Failed: requests to the server failed during this measurement. Over capacity: not run because this many requests at this context would exceed the server's KV cache.