Hugging Face's logo

mradermacher
/
Llama-3-Motif-102B-Instruct-i1-GGUF

Transformers
GGUF
Korean
English
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
31ee1b9
·
verified ·
1 Parent(s): e2b036d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +69 -0
README.md CHANGED
@@ -1,6 +1,75 @@
 
 
 
 
 
 
 
 
 
 
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/moreh/Llama-3-Motif-102B-Instruct
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: moreh/Llama-3-Motif-102B-Instruct
3
+ language:
4
+ - ko
5
+ - en
6
+ library_name: transformers
7
+ quantized_by: mradermacher
8
+ ---
9
+ ## About
10
+
11
  <!-- ### quantize_version: 2 -->
12
  <!-- ### output_tensor_quantised: 1 -->
13
  <!-- ### convert_type: hf -->
14
  <!-- ### vocab_type: -->
15
  <!-- ### tags: nicoboss -->
16
  weighted/imatrix quants of https://huggingface.co/moreh/Llama-3-Motif-102B-Instruct
17
+
18
+ <!-- provided-files -->
19
+ static quants are available at https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-GGUF
20
+ ## Usage
21
+
22
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
23
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
24
+ more details, including on how to concatenate multi-part files.
25
+
26
+ ## Provided Quants
27
+
28
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
29
+
30
+ | Link | Type | Size/GB | Notes |
31
+ |:-----|:-----|--------:|:------|
32
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 22.1 | for the desperate |
33
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 24.1 | mostly desperate |
34
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 27.5 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 30.5 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 32.1 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 34.8 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 35.2 | very low quality |
39
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 38.0 | IQ3_XXS probably better |
40
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 39.6 | lower quality |
41
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 42.2 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 44.4 | IQ3_XS probably better |
43
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 44.5 | beats Q3_K* |
44
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 46.1 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 49.4 | IQ3_S probably better |
46
+ | [PART 1](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 53.8 | IQ3_M probably better |
47
+ | [PART 1](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 54.8 | |
48
+ | [PART 1](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 58.0 | fast, low quality |
49
+ | [PART 1](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 58.2 | optimal size/speed/quality |
50
+ | [PART 1](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 61.4 | fast, recommended |
51
+ | [PART 1](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q4_1.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q4_1.gguf.part2of2) | i1-Q4_1 | 64.1 | |
52
+ | [PART 1](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 70.4 | |
53
+ | [PART 1](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 72.3 | |
54
+ | [PART 1](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-Motif-102B-Instruct-i1-GGUF/resolve/main/Llama-3-Motif-102B-Instruct.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 83.8 | practically like static Q6_K |
55
+
56
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
57
+ types (lower is better):
58
+
59
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
60
+
61
+ And here are Artefact2's thoughts on the matter:
62
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
63
+
64
+ ## FAQ / Model Request
65
+
66
+ See https://huggingface.co/mradermacher/model_requests for some answers to
67
+ questions you might have and/or if you want some other model quantized.
68
+
69
+ ## Thanks
70
+
71
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
72
+ me use its servers and providing upgrades to my workstation to enable
73
+ 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.
74
+
75
+ <!-- end -->