Upload complete model

README.md

@@ -9,7 +9,7 @@ pipeline_tag: text-generation
 ### CURRENTLY UPLOADING
 ### CURRENTLY UPLOADING
 
-**See DeepSeek-V3.2-Speciale 5.5bit MLX in action - [demonstration video - coming soon](https://youtube.com/xcreate)**
+**See DeepSeek-V3.2-Speciale 5.5bit MLX in action - [demonstration video](https://youtu.be/b6RgBIROK5o)**
 
 *q5.5bit quant typically achieves 1.141 perplexity in our testing*
 | Quantization | Perplexity |
@@ -24,12 +24,12 @@ pipeline_tag: text-generation
 ## Usage Notes
 
 * Tested remotely over the network via a M3 Ultra 512GB RAM using [Inferencer app v1.7.3](https://inferencer.com)
-* Memory usage: ~451 GB
-  * For a context window of more than 3000 tokens you can expand the VRAM limit:
+* Memory usage: ~450 GB
+  * For a larger context window you can expand the VRAM limit:
     * sudo sysctl iogpu.wired_limit_mb=507000
 * Expect ~16.5 tokens/s @ 1000 tokens
 * Quantized with a modified version of [MLX](https://github.com/ml-explore/mlx) 0.28
-* For more details see [demonstration video - coming soon](https://youtube.com/xcreate) or visit [DeepSeek-V3.2-Speciale](https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale).
+* For more details see [demonstration video - coming soon](https://youtu.be/b6RgBIROK5o) or visit [DeepSeek-V3.2-Speciale](https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale).
 
 ## Disclaimer