Hugging Face's logo

mradermacher
/
chat_noir-24b-v3-i1-GGUF

Transformers
GGUF
Portuguese
portuguese
português
PT-PT
português-europeu
direito
jurídico
chat
legaltech
virtuo-turing
cláudia-gil
octávio-viana
chat_noir
uncensored
instruction-following
portugal
imatrix
conversational
Model card Files
xet
 Community
mradermacher commited on
Commit
011ec21
·
verified ·
1 Parent(s): 5b8587d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -56,16 +56,23 @@ more details, including on how to concatenate multi-part files.
56
  | Link | Type | Size/GB | Notes |
57
  |:-----|:-----|--------:|:------|
58
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
 
59
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ1_M.gguf) | i1-IQ1_M | 5.9 | mostly desperate |
 
 
 
60
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ2_M.gguf) | i1-IQ2_M | 8.2 | |
61
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q2_K_S.gguf) | i1-Q2_K_S | 8.4 | very low quality |
62
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q2_K.gguf) | i1-Q2_K | 9.0 | IQ3_XXS probably better |
63
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality |
 
64
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ3_M.gguf) | i1-IQ3_M | 10.8 | |
65
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.6 | IQ3_S probably better |
 
66
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.9 | |
67
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.6 | optimal size/speed/quality |
68
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.4 | fast, recommended |
 
69
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q6_K.gguf) | i1-Q6_K | 19.4 | practically like static Q6_K |
70
 
71
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
56
  | Link | Type | Size/GB | Notes |
57
  |:-----|:-----|--------:|:------|
58
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
59
+ | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ1_S.gguf) | i1-IQ1_S | 5.4 | for the desperate |
60
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ1_M.gguf) | i1-IQ1_M | 5.9 | mostly desperate |
61
+ | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.6 | |
62
+ | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.3 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ2_S.gguf) | i1-IQ2_S | 7.6 | |
64
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ2_M.gguf) | i1-IQ2_M | 8.2 | |
65
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q2_K_S.gguf) | i1-Q2_K_S | 8.4 | very low quality |
66
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q2_K.gguf) | i1-Q2_K | 9.0 | IQ3_XXS probably better |
67
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality |
68
+ | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.5 | IQ3_XS probably better |
69
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ3_M.gguf) | i1-IQ3_M | 10.8 | |
70
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.6 | IQ3_S probably better |
71
+ | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.5 | IQ3_M probably better |
72
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.9 | |
73
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.6 | optimal size/speed/quality |
74
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.4 | fast, recommended |
75
+ | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.4 | |
76
  | [GGUF](https://huggingface.co/mradermacher/chat_noir-24b-v3-i1-GGUF/resolve/main/chat_noir-24b-v3.i1-Q6_K.gguf) | i1-Q6_K | 19.4 | practically like static Q6_K |
77
 
78
  Here is a handy graph by ikawrakow comparing some lower-quality quant