Hugging Face's logo

mradermacher
/
Meta-Llama-3-120b-LumiLumimaid-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
7a4358a
•
1 Parent(s): f5a12fa

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md CHANGED
@@ -1,5 +1,68 @@
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  weighted/imatrix quants of https://huggingface.co/gbueno86/Meta-Llama-3-120b-LumiLumimaid
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: gbueno86/Meta-Llama-3-120b-LumiLumimaid
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ quantized_by: mradermacher
7
+ ---
8
+ ## About
9
+
10
  <!-- ### quantize_version: 2 -->
11
  <!-- ### output_tensor_quantised: 1 -->
12
  <!-- ### convert_type: hf -->
13
  <!-- ### vocab_type: -->
14
  weighted/imatrix quants of https://huggingface.co/gbueno86/Meta-Llama-3-120b-LumiLumimaid
15
+
16
+ <!-- provided-files -->
17
+ static quants are available at https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-GGUF
18
+ ## Usage
19
+
20
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
21
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
22
+ more details, including on how to concatenate multi-part files.
23
+
24
+ ## Provided Quants
25
+
26
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
27
+
28
+ | Link | Type | Size/GB | Notes |
29
+ |:-----|:-----|--------:|:------|
30
+ | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 32.7 | |
31
+ | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-IQ2_XS.gguf) | i1-IQ2_XS | 36.3 | |
32
+ | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-IQ2_M.gguf) | i1-IQ2_M | 41.4 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q2_K.gguf) | i1-Q2_K | 45.2 | IQ3_XXS probably better |
34
+ | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 47.1 | lower quality |
35
+ | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-IQ3_XS.gguf.part2of2) | i1-IQ3_XS | 50.3 | |
36
+ | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 52.9 | IQ3_XS probably better |
37
+ | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-IQ3_S.gguf.part2of2) | i1-IQ3_S | 53.1 | beats Q3_K* |
38
+ | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 54.8 | |
39
+ | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 58.9 | IQ3_S probably better |
40
+ | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 64.1 | IQ3_M probably better |
41
+ | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 65.4 | |
42
+ | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 69.2 | fast, low quality |
43
+ | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 69.5 | optimal size/speed/quality |
44
+ | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 73.3 | fast, recommended |
45
+ | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 84.1 | |
46
+ | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 86.3 | |
47
+ | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3-120b-LumiLumimaid-i1-GGUF/resolve/main/Meta-Llama-3-120b-LumiLumimaid.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 100.1 | practically like static Q6_K |
48
+
49
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
50
+ types (lower is better):
51
+
52
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
53
+
54
+ And here are Artefact2's thoughts on the matter:
55
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
56
+
57
+ ## FAQ / Model Request
58
+
59
+ See https://huggingface.co/mradermacher/model_requests for some answers to
60
+ questions you might have and/or if you want some other model quantized.
61
+
62
+ ## Thanks
63
+
64
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
65
+ me use its servers and providing upgrades to my workstation to enable
66
+ this work in my free time.
67
+
68
+ <!-- end -->