Hugging Face's logo

mradermacher
/
Mixllama3-8x8b-Instruct-v0.1-i1-GGUF

Transformers
GGUF
English
text Generation
imatrix
conversational
Model card Files
xet
 Community
mradermacher commited on
Commit
de1a18b
·
verified ·
1 Parent(s): 8cbd10e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -40,14 +40,18 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 16.6 | very low quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 17.9 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.8 | lower quality |
 
 
43
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 21.0 | IQ3_XS probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 22.0 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 23.1 | IQ3_S probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.8 | IQ3_M probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.7 | |
 
48
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.4 | optimal size/speed/quality |
49
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 29.1 | fast, recommended |
50
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.9 | |
 
51
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 39.1 | practically like static Q6_K |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
40
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 16.6 | very low quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 17.9 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.8 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 20.0 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 21.0 | beats Q3_K* |
45
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 21.0 | IQ3_XS probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 22.0 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 23.1 | IQ3_S probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.8 | IQ3_M probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.7 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q4_0.gguf) | i1-Q4_0 | 27.2 | fast, low quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.4 | optimal size/speed/quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 29.1 | fast, recommended |
53
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.9 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.9 | |
55
  | [GGUF](https://huggingface.co/mradermacher/Mixllama3-8x8b-Instruct-v0.1-i1-GGUF/resolve/main/Mixllama3-8x8b-Instruct-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 39.1 | practically like static Q6_K |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant