AesSedai commited on
Commit
bdc63f5
·
verified ·
1 Parent(s): cbfdee0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -5,6 +5,10 @@ base_model:
5
 
6
  MoE-quants of GLM-5 (Q8_0 quantization default with routed experts quantized further)
7
 
 
 
 
 
8
  | Quant | Size | Mixture | PPL | KLD |
9
  | :--------- | :--------- | :------- | :------- | :--------- |
10
  | Q4_K_M | 432.80 GiB (4.93 BPW) | Q8_0-Q4_K-Q4_K-Q5_K | 8.7486 ± 0.17123 | TBD |
 
5
 
6
  MoE-quants of GLM-5 (Q8_0 quantization default with routed experts quantized further)
7
 
8
+ Note: running this GGUF requires pulling and compiling this llama.cpp PR: https://github.com/ggml-org/llama.cpp/pull/19460
9
+
10
+ More quants to come soon.
11
+
12
  | Quant | Size | Mixture | PPL | KLD |
13
  | :--------- | :--------- | :------- | :------- | :--------- |
14
  | Q4_K_M | 432.80 GiB (4.93 BPW) | Q8_0-Q4_K-Q4_K-Q5_K | 8.7486 ± 0.17123 | TBD |