Update README.md

README.md

@@ -16,11 +16,13 @@ Quantized using the [cleaned PIPPA](https://huggingface.co/datasets/royallab/PIP
 
 - [2.25bpw6h quants](https://huggingface.co/luigi86/magnum-72b-v1-exl2-rpcal/tree/2.25bpw6h) (tested and working on a single RTX 3090 24GiB at 16k context length)
 
-- [2.4bpw6h quants](https://huggingface.co/luigi86/magnum-72b-v1-exl2-rpcal/tree/2.4bpw6h) (may not load on 24GiB VRAM machines -- untested!)
+- [2.4bpw6h quants](https://huggingface.co/luigi86/magnum-72b-v1-exl2-rpcal/tree/2.4bpw6h) (may not load on 24GiB VRAM machines!)
 
 - [3.0bpw8h quants](https://huggingface.co/luigi86/magnum-72b-v1-exl2-rpcal/tree/3.0bpw8h)
 
-- [4.0bpw8h quants](https://huggingface.co/luigi86/magnum-72b-v1-exl2-rpcal/tree/4.0bpw8h) (tested and working on two 3090s with Q4 cache at 32k context)
+- [4.0bpw8h quants](https://huggingface.co/luigi86/magnum-72b-v1-exl2-rpcal/tree/4.0bpw8h) (tested and working on two 3090s at 32k context/cache)
+
+- [4.4bpw8h quants](https://huggingface.co/luigi86/magnum-72b-v1-exl2-rpcal/tree/4.4bpw8h) (tested and working on two 3090s at 32k context, 64k Q4 cache (for CFG or parallelism) with tabbyAPI)
 
 - [4.5bpw8h quants](https://huggingface.co/luigi86/magnum-72b-v1-exl2-rpcal/tree/4.5bpw8h)
 
@@ -29,6 +31,8 @@ Quantized using the [cleaned PIPPA](https://huggingface.co/datasets/royallab/PIP
 - [8.0bpw8h quants](https://huggingface.co/luigi86/magnum-72b-v1-exl2-rpcal/tree/8.0bpw8h)
 
 
+All tests performed on a headless Linux instance with no active desktop environment to maximize VRAM.
+
 Other quants available on request, feel free to ask!