⚡ Performance and Efficiency Benchmarks
This section reports the performance of MiniCPM-V 4.7 on NPU with FastFlowLM (FLM).
Note:
- Results are based on FastFlowLM v1.0.8.
- Under FLM’s default NPU power mode (Performance)
- Newer versions may deliver improved performance.
- Fine-tuned models show performance comparable to their base models.
Test System 1:
AMD Ryzen™ AI 5 340 (Kraken Point) with 64 GB DRAM; performance is comparable to other Kraken Point systems.
🚀 Decoding Speed (TPS, or Tokens per Second, starting @ different context lengths)
| Model | HW | 1k | 2k | 4k | 8k | 16k | 32k |
|---|---|---|---|---|---|---|---|
| MiniCPM-V-4.7-1B | NPU (FLM) | 47.7 | 45.9 | 43.0 | 32.7 | 31.6 | 23.8 |
🚀 Prefill Speed (TPS, or Tokens per Second, with different prompt lengths)
| Model | HW | 1k | 2k | 4k | 8k | 16k | 32k |
|---|---|---|---|---|---|---|---|
| MiniCPM-V-4.7-1B | NPU (FLM) | 1504.7 | 1624.0 | 1648.2 | 1808.8 | 1941.1 | 1666.3 |
🚀 Prefill TTFT with Image Input (Seconds)
Prefill time-to-first-token (TTFT) for MiniCPM-V-4.7-1B on NPU (FastFlowLM) with different image resolutions.
Mid Resolution Images:
| Model | HW | 720p (1280×720) | 1080p (1920×1080) |
|---|---|---|---|
| MiniCPM-V-4.7-1B | NPU (FLM) | 2.1 | 2.5 |
High Resolution Images:
| Model | HW | 2K (2560×1440) | 4K (3840×2160) |
|---|---|---|---|
| MiniCPM-V-4.7-1B | NPU (FLM) | 2.5 | 2.5 |
This test uses a short prompt: “Describe this image.”
TTFT stays flat from 1080p up: MiniCPM-V splits large images into at most 9 tiles, so higher resolutions add no extra image tokens.