Hugging Face's logo

mradermacher
/
shisa-v1-llama3-8b-i1-GGUF

Transformers
GGUF
English
Generated from Trainer
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
a9eb265
·
verified ·
1 Parent(s): 9a4d6a1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -42,15 +42,20 @@ more details, including on how to concatenate multi-part files.
42
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality |
43
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
 
45
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
 
46
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
47
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
 
50
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS |
51
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
52
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
 
53
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
 
54
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
55
 
56
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
42
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality |
43
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | |
46
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
48
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
49
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
53
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS |
54
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
55
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
56
+ | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | |
57
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
59
  | [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b-i1-GGUF/resolve/main/shisa-v1-llama3-8b.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
60
 
61
  Here is a handy graph by ikawrakow comparing some lower-quality quant