⚡ Performance and Efficiency Benchmarks

This section reports the performance of Qwen 3.8 on NPU with FastFlowLM (FLM).

Note:

• Results are based on FastFlowLM v1.0.7.
• Under FLM’s default NPU power mode (Performance)
• Newer versions may deliver improved performance.
• Fine-tuned models show performance comparable to their base models.
• qwen3.8-mtp:27b decodes with its built-in MTP draft head, so decoding speed is prompt-dependent — predictable text (code, structured output, long reasoning chains) accepts more drafts and decodes faster than highly creative text. See the model card for how speculation works.
• Benchmarks for this model are capped at 8k context.

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)

🚀 Prefill Speed (TPS, or Tokens per Second, with different prompt lengths)

🚀 Time to First Token (TTFT, Seconds, with different prompt lengths)

🚀 Prefill TTFT with Image Input (Seconds)

Prefill time-to-first-token (TTFT) for Qwen3.8-27B on NPU (FastFlowLM) with different image resolutions.

Mid Resolution Images:

This test uses a short prompt: “Describe this image.”