Hugging Face's logo

mradermacher
/
BigAurelian-v0.5-120b-32k-GGUF

Transformers
GGUF
English
aurelian
WinterGoddess
frankenmerge
120b
32k
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
3557bab
•
1 Parent(s): e88e199

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +55 -1
README.md CHANGED
@@ -1 +1,55 @@
1
- static quants of https://huggingface.co/llmixer/BigAurelian-v0.5-120b-32k
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ library_name: transformers
5
+ license: llama2
6
+ quantized_by: mradermacher
7
+ tags:
8
+ - aurelian
9
+ - WinterGoddess
10
+ - frankenmerge
11
+ - 120b
12
+ - 32k
13
+ ---
14
+ ## About
15
+
16
+ static quants of https://huggingface.co/llmixer/BigAurelian-v0.5-120b-32k
17
+
18
+ <!-- provided-files -->
19
+ ## Usage
20
+
21
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
22
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
23
+ more details, including on how to concatenate multi-part files.
24
+
25
+ ## Provided Quants
26
+
27
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
28
+
29
+ | Link | Type | Size/GB | Notes |
30
+ |:-----|:-----|--------:|:------|
31
+ | [GGUF](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q2_K.gguf) | Q2_K | 43.7 | |
32
+ | [GGUF](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.IQ3_XS.gguf) | IQ3_XS | 48.4 | |
33
+ | [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q3_K_S.gguf.part2of2) | Q3_K_S | 51.1 | |
34
+ | [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.IQ3_S.gguf.part2of2) | IQ3_S | 51.3 | fast, beats Q3_K* |
35
+ | [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.IQ3_M.gguf.part2of2) | IQ3_M | 53.0 | |
36
+ | [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q3_K_M.gguf.part2of2) | Q3_K_M | 57.0 | lower quality |
37
+ | [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q3_K_L.gguf.part2of2) | Q3_K_L | 62.1 | |
38
+ | [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.IQ4_XS.gguf.part2of2) | IQ4_XS | 63.9 | |
39
+ | [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q4_K_S.gguf.part2of2) | Q4_K_S | 67.2 | fast, medium quality |
40
+ | [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q4_K_M.gguf.part2of2) | Q4_K_M | 71.0 | fast, medium quality |
41
+ | [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q5_K_S.gguf.part2of2) | Q5_K_S | 81.4 | |
42
+ | [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q5_K_M.gguf.part2of2) | Q5_K_M | 83.6 | |
43
+ | [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q6_K.gguf.part3of3) | Q6_K | 97.0 | very good quality |
44
+ | [PART 1](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/BigAurelian-v0.5-120b-32k-GGUF/resolve/main/BigAurelian-v0.5-120b-32k.Q8_0.gguf.part3of3) | Q8_0 | 125.5 | fast, best quality |
45
+
46
+
47
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
48
+ types (lower is better):
49
+
50
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
51
+
52
+ And here are Artefact2's thoughts on the matter:
53
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
54
+
55
+ <!-- end -->