Hugging Face's logo

mradermacher
/
LwQ-10B-Instruct-GGUF

Transformers
GGUF
Safetensors
English
text-generation-inference
LwQ
Llama3.1
conversational
Model card Files Community
mradermacher commited on
Commit
03370b7
·
verified ·
1 Parent(s): 52b43a6

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -1
README.md CHANGED
@@ -7,6 +7,8 @@ license: llama3.1
7
  quantized_by: mradermacher
8
  tags:
9
  - text-generation-inference
 
 
10
  ---
11
  ## About
12
 
@@ -18,7 +20,7 @@ tags:
18
  static quants of https://huggingface.co/prithivMLmods/LwQ-10B-Instruct
19
 
20
  <!-- provided-files -->
21
- weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
22
  ## Usage
23
 
24
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -35,8 +37,14 @@ more details, including on how to concatenate multi-part files.
35
  | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q3_K_S.gguf) | Q3_K_S | 4.8 | |
36
  | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q3_K_M.gguf) | Q3_K_M | 5.3 | lower quality |
37
  | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q3_K_L.gguf) | Q3_K_L | 5.8 | |
 
38
  | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q4_K_S.gguf) | Q4_K_S | 6.2 | fast, recommended |
 
 
 
39
  | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q6_K.gguf) | Q6_K | 8.9 | very good quality |
 
 
40
 
41
  Here is a handy graph by ikawrakow comparing some lower-quality quant
42
  types (lower is better):
 
7
  quantized_by: mradermacher
8
  tags:
9
  - text-generation-inference
10
+ - LwQ
11
+ - safetensors
12
  ---
13
  ## About
14
 
 
20
  static quants of https://huggingface.co/prithivMLmods/LwQ-10B-Instruct
21
 
22
  <!-- provided-files -->
23
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/LwQ-10B-Instruct-i1-GGUF
24
  ## Usage
25
 
26
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
37
  | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q3_K_S.gguf) | Q3_K_S | 4.8 | |
38
  | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q3_K_M.gguf) | Q3_K_M | 5.3 | lower quality |
39
  | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q3_K_L.gguf) | Q3_K_L | 5.8 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.IQ4_XS.gguf) | IQ4_XS | 5.9 | |
41
  | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q4_K_S.gguf) | Q4_K_S | 6.2 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q5_K_S.gguf) | Q5_K_S | 7.5 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q5_K_M.gguf) | Q5_K_M | 7.7 | |
45
  | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q6_K.gguf) | Q6_K | 8.9 | very good quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.Q8_0.gguf) | Q8_0 | 11.5 | fast, best quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/LwQ-10B-Instruct-GGUF/resolve/main/LwQ-10B-Instruct.f16.gguf) | f16 | 21.6 | 16 bpw, overkill |
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):