Hugging Face's logo

mradermacher
/
Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF

Transformers
GGUF
Merge
programming
code generation
code
coding
coder
chat
brainstorm
brainstorm20x
mistral
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
93ba4ac
·
verified ·
1 Parent(s): c836700

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +111 -0
README.md CHANGED
@@ -1,3 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
@@ -7,3 +55,66 @@
7
  <!-- ### quants_skip: -->
8
  <!-- ### skip_mmproj: -->
9
  weighted/imatrix quants of https://huggingface.co/DavidAU/Mistral-Devstral-2505-CODER-Brainstorm40x-44B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DavidAU/Mistral-Devstral-2505-CODER-Brainstorm40x-44B
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
+ mradermacher:
31
+ readme_rev: 1
32
+ quantized_by: mradermacher
33
+ tags:
34
+ - merge
35
+ - programming
36
+ - code generation
37
+ - code
38
+ - coding
39
+ - coder
40
+ - chat
41
+ - code
42
+ - chat
43
+ - brainstorm
44
+ - brainstorm20x
45
+ - mistral
46
+ ---
47
+ ## About
48
+
49
  <!-- ### quantize_version: 2 -->
50
  <!-- ### output_tensor_quantised: 1 -->
51
  <!-- ### convert_type: hf -->
 
55
  <!-- ### quants_skip: -->
56
  <!-- ### skip_mmproj: -->
57
  weighted/imatrix quants of https://huggingface.co/DavidAU/Mistral-Devstral-2505-CODER-Brainstorm40x-44B
58
+
59
+ <!-- provided-files -->
60
+
61
+ ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF).***
62
+
63
+ static quants are available at https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-GGUF
64
+ ## Usage
65
+
66
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
67
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
68
+ more details, including on how to concatenate multi-part files.
69
+
70
+ ## Provided Quants
71
+
72
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
73
+
74
+ | Link | Type | Size/GB | Notes |
75
+ |:-----|:-----|--------:|:------|
76
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
77
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-IQ1_S.gguf) | i1-IQ1_S | 9.5 | for the desperate |
78
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-IQ1_M.gguf) | i1-IQ1_M | 10.4 | mostly desperate |
79
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 11.9 | |
80
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 13.2 | |
81
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-IQ2_S.gguf) | i1-IQ2_S | 13.6 | |
82
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-IQ2_M.gguf) | i1-IQ2_M | 14.8 | |
83
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 15.2 | very low quality |
84
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-Q2_K.gguf) | i1-Q2_K | 16.3 | IQ3_XXS probably better |
85
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 17.1 | lower quality |
86
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 18.2 | |
87
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 19.1 | IQ3_XS probably better |
88
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-IQ3_S.gguf) | i1-IQ3_S | 19.2 | beats Q3_K* |
89
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-IQ3_M.gguf) | i1-IQ3_M | 19.6 | |
90
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 21.1 | IQ3_S probably better |
91
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 22.9 | IQ3_M probably better |
92
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 23.5 | |
93
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-Q4_0.gguf) | i1-Q4_0 | 24.9 | fast, low quality |
94
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 25.0 | optimal size/speed/quality |
95
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 26.5 | fast, recommended |
96
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-Q4_1.gguf) | i1-Q4_1 | 27.5 | |
97
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 30.2 | |
98
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 31.0 | |
99
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Devstral-2505-CODER-Brainstorm40x-44B-i1-GGUF/resolve/main/Mistral-Devstral-2505-CODER-Brainstorm40x-44B.i1-Q6_K.gguf) | i1-Q6_K | 35.9 | practically like static Q6_K |
100
+
101
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
102
+ types (lower is better):
103
+
104
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
105
+
106
+ And here are Artefact2's thoughts on the matter:
107
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
108
+
109
+ ## FAQ / Model Request
110
+
111
+ See https://huggingface.co/mradermacher/model_requests for some answers to
112
+ questions you might have and/or if you want some other model quantized.
113
+
114
+ ## Thanks
115
+
116
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
117
+ me use its servers and providing upgrades to my workstation to enable
118
+ 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.
119
+
120
+ <!-- end -->