Update README.md

README.md

@@ -22,7 +22,7 @@ This repo contains select GGUF quants of [shisa-ai/shisa-v2-llama3.1-405b](https
 
 ## Provided Quants
 
-| Type    | Size (GB) |
+| Type    | Size (GiB) |
 |:--------|----------:|
 | IQ2_XXS | 100       |
 | IQ3_XS  | 155       |
@@ -35,7 +35,7 @@ This repo contains select GGUF quants of [shisa-ai/shisa-v2-llama3.1-405b](https
 ## Quant Quality
 All quants have been tested with JA MT-Bench (judged by GPT-4.1) as a rough guide for quality:
 
-| Quant        | Size(GB)| % Diff       | Overall  | Writing   | Roleplay | Reasoning | Math     | Coding   | Extraction | STEM     | Humanities |
+| Quant        | Size (GiB)| % Diff       | Overall  | Writing   | Roleplay | Reasoning | Math     | Coding   | Extraction | STEM     | Humanities |
 |--------------|--------:|-------------:|---------:|----------:|---------:|----------:|---------:|---------:|-----------:|---------:|-----------:|
 | Full FP16    | 810     |              | **9.13** | 9.25      | **9.55** | 8.15      | 8.90     | 9.10     | 9.65       | 9.10     | 9.35       |
 | IQ3_M        | 170     | -0.99        | 9.04     | 8.90      | 9.45     | 7.75      | 8.95     | 8.95     | 9.70       | **9.15** | 9.50       |
@@ -48,7 +48,11 @@ All quants have been tested with JA MT-Bench (judged by GPT-4.1) as a rough guid
 | *70B FP16*   | 140     | -7.89        | 8.41     | 7.95      | 9.05     | 6.25      | 8.30     | 8.25     | 9.70       | 8.70     | 9.05       |
 | IQ2_XXS      | 100     | -18.18       | 7.47     | 7.50      | 6.80     | 5.15      | 7.55     | 7.30     | 9.05       | 7.65     | 8.80       |
 
-Due to margin of error, you could probably fairly say that the IQ3_M, Q4_K_M, and Q8_0 GGUFs have almost no functional loss versus the FP16. Interestingly enough, while roleplay takes one of the biggest hits, writing seems to be improved on the Q4 and Q8? I think you'd really need to test. Interestingly the XS quants fare worses and the IQ4_XS does worse than the IQ3_M. The IQ2_XXS is trash and I included the 70B Full FP16 scores, but if the same pattern holds, I'd think you'd be better off with a 70B Q4_K_M (40GB) or IQ3_M (32GB).
+Due to margin of error, you could probably fairly say that the IQ3_M, Q4_K_M, and Q8_0 GGUFs have almost no functional loss versus the FP16.
+
+Interestingly enough, while roleplay takes one of the biggest hits, writing seems to be improved on the Q4 and Q8? I think you'd really need to test more (more samples, more runs, more evals) to really see what's going on. Also interestingly the XS quants track pretty consistently, with the IQ4_XS doing worse than the IQ3_M.
+
+The IQ2_XXS scores extremely poorly. I included the 70B Full FP16 scores as a baseline and I'd expect you'd be better off running a decent Shisa V2 70B Q4_K_M (40GB) or IQ3_M (32GB) vs the IQ2. 
 
 In an ideal world, of course, you should test different quants on your downstream tasks, but I understand that that's not always an option. Based on this testing though, if you had to pick on bang/buck quant blind, I'd start with the IQ3_M.