Hugging Face's logo

mradermacher
/
LLaMA2-13B-Tiefighter-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
1a51049
•
1 Parent(s): d34be5b

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -24,6 +24,7 @@ more details, including on how to concatenate multi-part files.
24
  | Link | Type | Size/GB | Notes |
25
  |:-----|:-----|--------:|:------|
26
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-IQ1_S.gguf) | i1-IQ1_S | 3.2 | for the desperate |
 
27
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.9 | |
28
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.2 | |
29
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-IQ2_S.gguf) | i1-IQ2_S | 4.5 | |
@@ -35,11 +36,14 @@ more details, including on how to concatenate multi-part files.
35
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.0 | IQ3_XS probably better |
36
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-IQ3_M.gguf) | i1-IQ3_M | 6.3 | |
37
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.6 | IQ3_S probably better |
 
38
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.2 | IQ3_M probably better |
 
39
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.7 | optimal size/speed/quality |
40
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.2 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.3 | |
42
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.5 | |
 
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant
45
  types (lower is better):
 
24
  | Link | Type | Size/GB | Notes |
25
  |:-----|:-----|--------:|:------|
26
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-IQ1_S.gguf) | i1-IQ1_S | 3.2 | for the desperate |
27
+ | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-IQ1_M.gguf) | i1-IQ1_M | 3.2 | mostly desperate |
28
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.9 | |
29
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.2 | |
30
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-IQ2_S.gguf) | i1-IQ2_S | 4.5 | |
 
36
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.0 | IQ3_XS probably better |
37
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-IQ3_M.gguf) | i1-IQ3_M | 6.3 | |
38
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.6 | IQ3_S probably better |
39
+ | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.1 | |
40
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.2 | IQ3_M probably better |
41
+ | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q4_0.gguf) | i1-Q4_0 | 7.5 | fast, low quality |
42
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.7 | optimal size/speed/quality |
43
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.2 | fast, recommended |
44
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.3 | |
45
  | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.5 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Tiefighter-i1-GGUF/resolve/main/LLaMA2-13B-Tiefighter.i1-Q6_K.gguf) | i1-Q6_K | 10.8 | practically like static Q6_K |
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):