Hugging Face's logo

mradermacher
/
Llama-Sentient-3.2-3B-Instruct-i1-GGUF

Transformers
GGUF
English
Llama
Llama-Cpp
Llama3.2
Instruct
3B
bin
Sentient
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
6400c24
•
1 Parent(s): e0fb44d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +80 -0
README.md CHANGED
@@ -1,6 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/prithivMLmods/Llama-Sentient-3.2-3B-Instruct
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: prithivMLmods/Llama-Sentient-3.2-3B-Instruct
3
+ datasets:
4
+ - mlabonne/lmsys-arena-human-preference-55k-sharegpt
5
+ language:
6
+ - en
7
+ library_name: transformers
8
+ license: creativeml-openrail-m
9
+ quantized_by: mradermacher
10
+ tags:
11
+ - Llama
12
+ - Llama-Cpp
13
+ - Llama3.2
14
+ - Instruct
15
+ - 3B
16
+ - bin
17
+ - Sentient
18
+ ---
19
+ ## About
20
+
21
  <!-- ### quantize_version: 2 -->
22
  <!-- ### output_tensor_quantised: 1 -->
23
  <!-- ### convert_type: hf -->
24
  <!-- ### vocab_type: -->
25
  <!-- ### tags: nicoboss -->
26
  weighted/imatrix quants of https://huggingface.co/prithivMLmods/Llama-Sentient-3.2-3B-Instruct
27
+
28
+ <!-- provided-files -->
29
+ static quants are available at https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-GGUF
30
+ ## Usage
31
+
32
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
33
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
34
+ more details, including on how to concatenate multi-part files.
35
+
36
+ ## Provided Quants
37
+
38
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
39
+
40
+ | Link | Type | Size/GB | Notes |
41
+ |:-----|:-----|--------:|:------|
42
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate |
43
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate |
44
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better |
50
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* |
52
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better |
53
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better |
55
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better |
56
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 2.0 | fast on arm, low quality |
58
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 2.0 | fast on arm+i8mm, low quality |
59
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 2.0 | fast on arm+sve, low quality |
60
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality |
61
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality |
62
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended |
63
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/Llama-Sentient-3.2-3B-Instruct-i1-GGUF/resolve/main/Llama-Sentient-3.2-3B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | practically like static Q6_K |
66
+
67
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
68
+ types (lower is better):
69
+
70
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
71
+
72
+ And here are Artefact2's thoughts on the matter:
73
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
74
+
75
+ ## FAQ / Model Request
76
+
77
+ See https://huggingface.co/mradermacher/model_requests for some answers to
78
+ questions you might have and/or if you want some other model quantized.
79
+
80
+ ## Thanks
81
+
82
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
83
+ me use its servers and providing upgrades to my workstation to enable
84
+ 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.
85
+
86
+ <!-- end -->