Update README.md

README.md

@@ -33,54 +33,50 @@ Building on top of **TTM-R1** and **TTM-R2**, we introduce the next generation o
 
 ---
 
-## Accuracy & Speed
+## Architecture Overview
 
-**Granite-TTM-R3** is engineered to achieve a strong balance between **state-of-the-art accuracy** and **extreme inference efficiency**, making it well-suited for real-world, high-throughput deployments.
+Granite-TTM adopts a mixture-of-experts paradigm composed of models with varying complexities [1-35M and Lite: 1-18M parameters] — coupled with a lightweight routing mechanism that automatically selects or blends the most suitable expert based on input data characteristics.
 
-### Accuracy on GIFT-Eval 
+This enables adaptive model selection, improving both accuracy and efficiency across diverse time-series scenarios.
+
+The architecture is built on efficient mixer-based designs that avoid expensive self-attention. Instead, Granite-TTM-R3 leverages linear gating-based attention mechanisms to capture temporal dependencies with significantly lower computational overhead.
 
-- Maintains **top-tier performance** on the GIFT-Eval benchmarks. 
+This combination allows **Granite-TTM-R3** to deliver scalable, adaptive, and ultra-fast forecasting performance suitable for real-time and large-scale deployments.
 
-**Fine-tuned FM**
+---
 
-- MASE: **0.718**
-- CRPS: **514**
+## Accuracy & Speed
 
+**Granite-TTM-R3** is engineered to achieve a strong balance between **state-of-the-art accuracy** and **extreme inference efficiency**, making it well-suited for real-world, high-throughput deployments.
 
-**Pre-trained FM**
+### Accuracy on GIFT-Eval 
 
-- MASE: **0.727**
-- CRPS: **523**
+- Maintains **top-tier performance** on the GIFT-Eval leaderboard. 
+- **Fine-tuned FM**:  
+  - MASE: **0.718** | CRPS: **0.514**  
+  - *(Lite)* MASE: **0.719** | CRPS: **0.514**
+- **Pre-trained FM**:  
+  - MASE: **0.727** | CRPS: **0.523**  
+  - *(Lite)* MASE: **0.733** | CRPS: **0.524**
 
 ---
 
-## ⚡ Inference Throughput
+## Inference Throughput
 
 **Granite-TTM-R3** delivers orders-of-magnitude faster inference compared to existing popular SOTA models.
 
-### GPU Throughput
-
+#### 🖥️ GPU Throughput
 - Typical SOTA models: **~20–500 samples/sec**
 - **Granite-TTM-R3**: **~7,500 samples/sec**
+- **Granite-TTM-R3 Lite**: **~18,000 samples/sec**
 
-### CPU Throughput
-
+#### 💻 CPU Throughput
 - Typical SOTA models: **~1–20 samples/sec**
 - **Granite-TTM-R3**: **~180 samples/sec**
+- **Granite-TTM-R3 Lite**: **~800 samples/sec**
 
-**Granite-TTM-R3 achieves ~15× speedup** over many existing approaches, without compromising accuracy, setting a strong benchmark for fast and reliable time-series forecasting.
-
----
-
-## Architecture Overview
-
-Granite-TTM adopts a mixture-of-experts paradigm composed of models with varying complexities — approximately **1M–35M parameters** — coupled with a lightweight routing mechanism that automatically selects or blends the most suitable expert based on input data characteristics.
-
-This enables adaptive model selection, improving both accuracy and efficiency across diverse time-series scenarios.
-
-The architecture is built on efficient mixer-based designs that avoid expensive self-attention. Instead, Granite-TTM-R3 leverages linear gating-based attention mechanisms to capture temporal dependencies with significantly lower computational overhead.
+👉 **Granite-TTM-R3 models achieves ~15–50× speedup** over many existing approaches, **without compromising accuracy**, setting a new benchmark for fast and reliable time-series forecasting.
 
-This combination allows **Granite-TTM-R3** to deliver scalable, adaptive, and ultra-fast forecasting performance suitable for real-time and large-scale deployments.
 
 ---