Hugging Face's logo

mradermacher
/
Mistral-Small-3.1-24B-Base-2503-i1-GGUF

Transformers
GGUF
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
edf8e67
·
verified ·
1 Parent(s): cff2014

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +92 -0
README.md CHANGED
@@ -1,6 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: nicoboss -->
6
  weighted/imatrix quants of https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Base-2503
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-Small-3.1-24B-Base-2503
3
+ language:
4
+ - en
5
+ - fr
6
+ - de
7
+ - es
8
+ - pt
9
+ - it
10
+ - ja
11
+ - ko
12
+ - ru
13
+ - zh
14
+ - ar
15
+ - fa
16
+ - id
17
+ - ms
18
+ - ne
19
+ - pl
20
+ - ro
21
+ - sr
22
+ - sv
23
+ - tr
24
+ - uk
25
+ - vi
26
+ - hi
27
+ - bn
28
+ library_name: transformers
29
+ license: apache-2.0
30
+ quantized_by: mradermacher
31
+ ---
32
+ ## About
33
+
34
  <!-- ### quantize_version: 2 -->
35
  <!-- ### output_tensor_quantised: 1 -->
36
  <!-- ### convert_type: hf -->
37
  <!-- ### vocab_type: -->
38
  <!-- ### tags: nicoboss -->
39
  weighted/imatrix quants of https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Base-2503
40
+
41
+ <!-- provided-files -->
42
+ static quants are available at https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-GGUF
43
+ ## Usage
44
+
45
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
46
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
47
+ more details, including on how to concatenate multi-part files.
48
+
49
+ ## Provided Quants
50
+
51
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
52
+
53
+ | Link | Type | Size/GB | Notes |
54
+ |:-----|:-----|--------:|:------|
55
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-IQ1_S.gguf) | i1-IQ1_S | 5.4 | for the desperate |
56
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-IQ1_M.gguf) | i1-IQ1_M | 5.9 | mostly desperate |
57
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.6 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.3 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-IQ2_S.gguf) | i1-IQ2_S | 7.6 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-IQ2_M.gguf) | i1-IQ2_M | 8.2 | |
61
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-Q2_K_S.gguf) | i1-Q2_K_S | 8.4 | very low quality |
62
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-Q2_K.gguf) | i1-Q2_K | 9.0 | IQ3_XXS probably better |
63
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality |
64
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.0 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.5 | IQ3_XS probably better |
66
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-IQ3_S.gguf) | i1-IQ3_S | 10.5 | beats Q3_K* |
67
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-IQ3_M.gguf) | i1-IQ3_M | 10.8 | |
68
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.6 | IQ3_S probably better |
69
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.5 | IQ3_M probably better |
70
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.9 | |
71
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-Q4_0.gguf) | i1-Q4_0 | 13.6 | fast, low quality |
72
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.6 | optimal size/speed/quality |
73
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.4 | fast, recommended |
74
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-Q4_1.gguf) | i1-Q4_1 | 15.0 | |
75
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.4 | |
76
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-Q5_K_M.gguf) | i1-Q5_K_M | 16.9 | |
77
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Small-3.1-24B-Base-2503-i1-GGUF/resolve/main/Mistral-Small-3.1-24B-Base-2503.i1-Q6_K.gguf) | i1-Q6_K | 19.4 | practically like static Q6_K |
78
+
79
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
80
+ types (lower is better):
81
+
82
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
83
+
84
+ And here are Artefact2's thoughts on the matter:
85
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
86
+
87
+ ## FAQ / Model Request
88
+
89
+ See https://huggingface.co/mradermacher/model_requests for some answers to
90
+ questions you might have and/or if you want some other model quantized.
91
+
92
+ ## Thanks
93
+
94
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
95
+ me use its servers and providing upgrades to my workstation to enable
96
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
97
+
98
+ <!-- end -->