Hugging Face's logo

mradermacher
/
Mistral-Small-3.1-24B-Base-2503-GGUF

Transformers
GGUF
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
29bd6cf
·
verified ·
1 Parent(s): 0c929e1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -1
README.md CHANGED
@@ -39,7 +39,7 @@ quantized_by: mradermacher
39
  static quants of https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Base-2503
40
 
41
  <!-- provided-files -->
42
- 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.
43
  ## Usage
44
 
45
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -55,7 +55,14 @@ more details, including on how to concatenate multi-part files.
55
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q2_K.gguf) | Q2_K | 9.0 | |
56
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q3_K_S.gguf) | Q3_K_S | 10.5 | |
57
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q3_K_M.gguf) | Q3_K_M | 11.6 | lower quality |
 
 
58
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q4_K_S.gguf) | Q4_K_S | 13.6 | fast, recommended |
 
 
 
 
 
59
 
60
  Here is a handy graph by ikawrakow comparing some lower-quality quant
61
  types (lower is better):
 
39
  static quants of https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Base-2503
40
 
41
  <!-- provided-files -->
42
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF
43
  ## Usage
44
 
45
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
55
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q2_K.gguf) | Q2_K | 9.0 | |
56
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q3_K_S.gguf) | Q3_K_S | 10.5 | |
57
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q3_K_M.gguf) | Q3_K_M | 11.6 | lower quality |
58
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q3_K_L.gguf) | Q3_K_L | 12.5 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.IQ4_XS.gguf) | IQ4_XS | 13.0 | |
60
  | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q4_K_S.gguf) | Q4_K_S | 13.6 | fast, recommended |
61
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q4_K_M.gguf) | Q4_K_M | 14.4 | fast, recommended |
62
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q5_K_S.gguf) | Q5_K_S | 16.4 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q5_K_M.gguf) | Q5_K_M | 16.9 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q6_K.gguf) | Q6_K | 19.4 | very good quality |
65
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.Q8_0.gguf) | Q8_0 | 25.2 | fast, best quality |
66
 
67
  Here is a handy graph by ikawrakow comparing some lower-quality quant
68
  types (lower is better):