Hugging Face's logo

mradermacher
/
Mistral-Large-Instruct-2407-i1-GGUF

Transformers
GGUF
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
b094b66
•
1 Parent(s): 235386a

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +75 -0
README.md CHANGED
@@ -1,6 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-Large-Instruct-2407
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-Large-Instruct-2407
3
+ language:
4
+ - en
5
+ - fr
6
+ - de
7
+ - es
8
+ - it
9
+ - pt
10
+ - zh
11
+ - ja
12
+ - ru
13
+ - ko
14
+ library_name: transformers
15
+ license: other
16
+ license_link: https://mistral.ai/licenses/MRL-0.1.md
17
+ license_name: mrl
18
+ quantized_by: mradermacher
19
+ ---
20
+ ## About
21
+
22
  <!-- ### quantize_version: 2 -->
23
  <!-- ### output_tensor_quantised: 1 -->
24
  <!-- ### convert_type: hf -->
25
  <!-- ### vocab_type: -->
26
  <!-- ### tags: nicoboss -->
27
  weighted/imatrix quants of https://huggingface.co/mistralai/Mistral-Large-Instruct-2407
28
+
29
+ <!-- provided-files -->
30
+ static quants are available at https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-GGUF
31
+ ## Usage
32
+
33
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
34
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
35
+ more details, including on how to concatenate multi-part files.
36
+
37
+ ## Provided Quants
38
+
39
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
40
+
41
+ | Link | Type | Size/GB | Notes |
42
+ |:-----|:-----|--------:|:------|
43
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 32.5 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-IQ2_XS.gguf) | i1-IQ2_XS | 36.2 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-IQ2_M.gguf) | i1-IQ2_M | 41.7 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q2_K.gguf) | i1-Q2_K | 45.3 | IQ3_XXS probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 47.1 | lower quality |
48
+ | [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-IQ3_XS.gguf.part2of2) | i1-IQ3_XS | 50.2 | |
49
+ | [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 52.9 | IQ3_XS probably better |
50
+ | [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-IQ3_S.gguf.part2of2) | i1-IQ3_S | 53.1 | beats Q3_K* |
51
+ | [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 55.4 | |
52
+ | [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 59.2 | IQ3_S probably better |
53
+ | [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 64.7 | IQ3_M probably better |
54
+ | [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 65.5 | |
55
+ | [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 69.4 | fast, low quality |
56
+ | [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 69.7 | optimal size/speed/quality |
57
+ | [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 73.3 | fast, recommended |
58
+ | [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 84.5 | |
59
+ | [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 86.6 | |
60
+ | [PART 1](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Mistral-Large-Instruct-2407-i1-GGUF/resolve/main/Mistral-Large-Instruct-2407.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 100.7 | practically like static Q6_K |
61
+
62
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
63
+ types (lower is better):
64
+
65
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
66
+
67
+ And here are Artefact2's thoughts on the matter:
68
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
69
+
70
+ ## FAQ / Model Request
71
+
72
+ See https://huggingface.co/mradermacher/model_requests for some answers to
73
+ questions you might have and/or if you want some other model quantized.
74
+
75
+ ## Thanks
76
+
77
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
78
+ me use its servers and providing upgrades to my workstation to enable
79
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.
80
+
81
+ <!-- end -->