morikomorizz commited on
Commit
74ce34a
·
verified ·
1 Parent(s): 06d6af1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -9,11 +9,11 @@ base_model:
9
 
10
  This repository contains the **GGUF** quantized files for **[zai-org/GLM-5.2](https://huggingface.co/zai-org/GLM-5.2)**.
11
 
12
- | Version | FFN Exps Gate/Up/Down | Token Embedding | Output Weight | Size |
13
- | :--- | :--- | :--- | :--- |
14
- | IQ2_M | IQ2_XXS/IQ2_XXS/IQ3_S | Q8_0 | Q8_0 | 262 GB |
15
- | MixQ5-IQ3_S | IQ3_S/IQ3_S/Q5_K | BF16 | BF16 | 431 GB |
16
- | MXFP4 | MXFP4/MXFP4/MXFP4 | BF16 | BF16 | 443 GB |
17
 
18
  **Note:** The front FFN layers in the initial blocks are all assigned Q8_0, and the rest of the core tensors remain in BF16 and FP32.
19
 
 
9
 
10
  This repository contains the **GGUF** quantized files for **[zai-org/GLM-5.2](https://huggingface.co/zai-org/GLM-5.2)**.
11
 
12
+ | Version | FFN Exps Gate-Up-Down | Token Embedding | Output Weight | Size |
13
+ | :--- | :--- | :--- | :--- | :--- |
14
+ | IQ2_M | IQ2_XXS-IQ2_XXS-IQ3_S | Q8_0 | Q8_0 | 262 GB |
15
+ | MixQ5-IQ3_S | IQ3_S-IQ3_S-Q5_K | BF16 | BF16 | 431 GB |
16
+ | MXFP4 | MXFP4-MXFP4-MXFP4 | BF16 | BF16 | 443 GB |
17
 
18
  **Note:** The front FFN layers in the initial blocks are all assigned Q8_0, and the rest of the core tensors remain in BF16 and FP32.
19