diff --git a/index.html b/index.html index e9ccf08..f54d700 100755 --- a/index.html +++ b/index.html @@ -1598,10 +1598,24 @@

Figure 3: Memory Efficiency Breakdown

-
- pie title Qwen3-235B Memory Usage (Traditional vs Moxiegen) - "Traditional FP32 (940 GB)" : 940 - "Moxiegen Compressed (47 GB)" : 47 +
+ + + + + + + + + + 95% + memory reduction + + + Traditional FP32 — 940 GB + + Moxiegen — 47 GB +

Figure 3: Dramatic memory reduction achieved through pointer-based weight mapping

@@ -1665,22 +1679,61 @@

Figure 4: Energy Consumption Comparison

-
- graph LR - subgraph "Traditional A100 Cluster" - A["12x A100 GPUs (~4,200W)"] --> B["Annual Energy: ~36,792 kWh"] - B --> C["CO2 Emissions: ~16.5 tons/year"] - end - subgraph "Moxiegen Method" - D["1x RTX 3060 (~170W)"] --> E["Annual Energy: ~1,489 kWh"] - E --> F["CO2 Emissions: ~0.67 tons/year"] - end - style A fill:#7f1d1d,color:#f8fafc,stroke:#f87171 - style B fill:#7f1d1d,color:#f8fafc,stroke:#f87171 - style C fill:#7f1d1d,color:#f8fafc,stroke:#f87171 - style D fill:#064e3b,color:#f8fafc,stroke:#34d399 - style E fill:#064e3b,color:#f8fafc,stroke:#34d399 - style F fill:#064e3b,color:#f8fafc,stroke:#34d399 +
+ + + + + + + Traditional A100 Cluster + + + + 12x A100 GPUs + + + Power Draw + 4,200W + + + + + + Annual Energy + 36,792 kWh + + + CO2 Emissions + 16.5 t/yr + + + Moxiegen Method + + + + 1x RTX 3060 + + + Power Draw + 170W + + + + + + Annual Energy + 1,489 kWh + + + CO2 Emissions + 0.67 t/yr + + + › + 96% + less energy +

Figure 4: Environmental impact comparison showing 96% reduction in energy consumption