Prefill and token generation speed
Studio M3 Ultra 512GB with Qwen3.8-Flash-Next: prefill and generation speed
Last updated
819 GB/s
Active 6B / Sangju 180B
50 ~ 70.3 tok/sDecode speed
Model fully loaded (107.13GB / 480GB)
First token (TTFT)
3.3 to 4.5 secondsContext 4,096 input tokens included
Prefill speed
910 ~ 1,229 tok/s3.3 to 4.5 seconds (Benchmark-calibrated)
Total time (E2E)
Approximately 5.0 to 6.8 seconds117 output tokens included
Press Play to process the input and generate the answer.
Ready
Expand settings Settings4-bit · 4K · Baseline decodeCollapse
QuantizationNeed 107.13GB
Input context4K tokens
Baseline
Baseline
Sample question:
117 output tokensCheck configuration
Studio M3 Ultra 512GB · Memory 512GB
Qwen3.8-Flash-Next 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
Qwen Flash Next on Mac Studio M5 Ultra 512GB
103.5 ~ 184.1 tok/s · 0.65 to 1.2 seconds
RTX PRO 6000 96GB × Qwen3.8-Flash-Next
175.2 ~ 340.0 tok/s · 1.2 to 2.2 seconds
Qwen Flash Next on two DGX Sparks: what changes?
16.7 ~ 33.8 tok/s · 1.7 to 4.3 seconds
2× RTX 5090 64GB (PCIe) × Qwen3.8-Flash-Next
127.7 ~ 263.9 tok/s · 0.46 to 0.94 seconds