Replace llama with Grantite

README.md

@@ -11,25 +11,20 @@ Our flagship products focus on answering hard questions about code:
 
 ---
 
-
 ## Available Models
 
 | Model Family | Parameters | Model | Quantization | Direct Download |
-|-------------|-------|-------|--------------|-----------------|
-| Llama 3.2 | 1 Billion | Llama-3.2-1B-Instruct | Q8_0 | [Download](https://huggingface.co/SciTools/Llama3.2/resolve/main/Llama-3.2-1B-Instruct-Q8_0.gguf?download=true) |
-| Llama 3.2 | 3 Billion | Llama-3.2-3B-Instruct | Q8_0 | [Download](https://huggingface.co/SciTools/Llama3.2/resolve/main/Llama-3.2-3B-Instruct-Q8_0.gguf?download=true) |
-| Llama 3.2 | 8 Billion | Llama-3.2-8B-Instruct | Q5_K_M | [Download](https://huggingface.co/SciTools/Llama3.2/resolve/main/Llama-3.2-8B-Instruct-Q5_K_M.gguf?download=true) |
-| Qwen3 | .6 Billion | Qwen3-0.6B | Q4_K_M | [Download](https://huggingface.co/SciTools/Qwen3/resolve/main/Qwen3-0.6B-Q4_K_M.gguf?download=true) |
+|-------------|------------|-------|--------------|-----------------|
+| Granite 4 | 1 Billion | Granite-4.0-1B | Q4 (GGUF) | [Download](https://huggingface.co/ibm-granite/granite-4.0-1b-GGUF) |
+| Granite 4 | 3 Billion | Granite-4.0-Micro | Q4_K_M | [Download](https://huggingface.co/unsloth/granite-4.0-micro-Q4_K_M.gguf) |
 | Qwen3 | 1.7 Billion | Qwen3-1.7B | Q4_K_M | [Download](https://huggingface.co/SciTools/Qwen3/resolve/main/Qwen3-1.7B-Q4_K_M.gguf?download=true) |
 | Qwen3 | 4 Billion | Qwen3-4B | Q4_K_M | [Download](https://huggingface.co/SciTools/Qwen3/resolve/main/Qwen3-4B-Q4_K_M.gguf?download=true) |
 | Qwen3 | 8 Billion | Qwen3-8B | Q4_K_M | [Download](https://huggingface.co/SciTools/Qwen3/resolve/main/Qwen3-8B-Q4_K_M.gguf?download=true) |
-| Qwen3 | 14 Billion | Qwen3-14B | Q4_K_M | [Download](https://huggingface.co/SciTools/Qwen3/resolve/main/Qwen3-14B-Q4_K_M.gguf?download=true) |
 
 [Help me choose a local LLM for Understand](https://support.scitools.com/support/solutions/articles/70000680303-choosing-a-local-llm-for-understand)
 
 ---
 
-
 ## What We Build
 
 **Understand**  
@@ -52,6 +47,7 @@ We focus on **local, transparent, and developer-controlled AI**.
 The models hosted here are provided to support SciTools products as well as other GGUF-compatible tools.
 
 ---
+
 ## Who Uses SciTools
 
 SciTools products are used by: