Hugging Face's logo

MikeRoz
/
Qwen3-Coder-480B-A35B-Instruct-exl3

Text Generation
exllamav3
exl3
Model card Files
xet
Community
1
MikeRoz commited on
Commit
57922d7
·
verified ·
1 Parent(s): 5a04e2a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -12,5 +12,6 @@ tags:
12
  Exllamav3 quantization of [Qwen/Qwen3-Coder-480B-A35B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct)
13
 
14
  [2.00 bpw h6](https://huggingface.co/MikeRoz/Qwen3-Coder-480B-A35B-Instruct-exl3/tree/2.00bpw_H6) 114.396 GiB
 
15
 
16
  The 2.00bpw quant will fit in six 24 GB cards with 40k of fp16 context.
 
12
  Exllamav3 quantization of [Qwen/Qwen3-Coder-480B-A35B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct)
13
 
14
  [2.00 bpw h6](https://huggingface.co/MikeRoz/Qwen3-Coder-480B-A35B-Instruct-exl3/tree/2.00bpw_H6) 114.396 GiB
15
+ [3.00 bpw h6](https://huggingface.co/MikeRoz/Qwen3-Coder-480B-A35B-Instruct-exl3/tree/2.00bpw_H6) 170.069 GiB
16
 
17
  The 2.00bpw quant will fit in six 24 GB cards with 40k of fp16 context.