Hugging Face's logo

cmh
/
phi-4_exl2

Text Generation
English
Model card Files
xet
Community
cmh commited on
Commit
978ea98
·
verified ·
1 Parent(s): 9be7a51

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ pipeline_tag: text-generation
13
  [ExLlamaV2 is an inference library for running local LLMs on modern consumer GPUs.](https://github.com/turboderp-org/exllamav2)
14
 
15
 
16
- | | Quant type | File Size | ~Vram*|
17
  | -------- | ---------- | --------- | -------- |
18
  | [phi-4 hb8 3bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_3bpw) | 3 bits per weight | 6.66 GB | **10,3 GB** |
19
  | [phi-4 hb8 4bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_4bpw) | 4 bits per weight | 8.36 GB | **11,9 GB** |
 
13
  [ExLlamaV2 is an inference library for running local LLMs on modern consumer GPUs.](https://github.com/turboderp-org/exllamav2)
14
 
15
 
16
+ | | Quant type | File Size | Vram*|
17
  | -------- | ---------- | --------- | -------- |
18
  | [phi-4 hb8 3bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_3bpw) | 3 bits per weight | 6.66 GB | **10,3 GB** |
19
  | [phi-4 hb8 4bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_4bpw) | 4 bits per weight | 8.36 GB | **11,9 GB** |