Hugging Face's logo

mradermacher
/
L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
911f651
·
verified ·
1 Parent(s): 0ee64b1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +82 -0
README.md CHANGED
@@ -1,6 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/PJMixers-Dev/L3.2-Instruct-Thinking-v0.1-1B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: PJMixers-Dev/L3.2-Instruct-Thinking-v0.1-1B
3
+ datasets:
4
+ - PJMixers-Dev/Weyaxi_HelpSteer-filtered-gemini-2.0-flash-thinking-exp-1219-CustomShareGPT
5
+ - PJMixers-Dev/lmsys-chat-1m-gemini-2.0-flash-thinking-exp-1219-CustomShareGPT
6
+ - PJMixers-Dev/allenai_WildChat-1M-gemini-2.0-flash-thinking-exp-1219-CustomShareGPT
7
+ - PJMixers-Dev/allenai_WildChat-1M-gemini-2.0-flash-exp-ShareGPT
8
+ - PJMixers-Dev/grimulkan_theory-of-mind-gemini-2.0-flash-exp-ShareGPT
9
+ - PJMixers-Dev/grimulkan_physical-reasoning-gemini-2.0-flash-exp-ShareGPT
10
+ - PJMixers-Dev/WizardLMTeam_WizardLM_evol_instruct_70k-gemini-2.0-flash-thinking-exp-1219-CustomShareGPT
11
+ - PJMixers-Dev/WizardLMTeam_WizardLM_evol_instruct_70k-gemini-2.0-flash-exp-ShareGPT
12
+ - PJMixers-Dev/allenai_WildChat-1M-gemini-exp-1206-ShareGPT
13
+ - PJMixers-Dev/grimulkan_theory-of-mind-gemini-exp-1206-ShareGPT
14
+ - PJMixers-Dev/FreedomIntelligence_medical-o1-reasoning-SFT-CustomShareGPT
15
+ language:
16
+ - en
17
+ library_name: transformers
18
+ license: llama3.2
19
+ quantized_by: mradermacher
20
+ ---
21
+ ## About
22
+
23
  <!-- ### quantize_version: 2 -->
24
  <!-- ### output_tensor_quantised: 1 -->
25
  <!-- ### convert_type: hf -->
26
  <!-- ### vocab_type: -->
27
  <!-- ### tags: nicoboss -->
28
  weighted/imatrix quants of https://huggingface.co/PJMixers-Dev/L3.2-Instruct-Thinking-v0.1-1B
29
+
30
+ <!-- provided-files -->
31
+ static quants are available at https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-GGUF
32
+ ## Usage
33
+
34
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
35
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
36
+ more details, including on how to concatenate multi-part files.
37
+
38
+ ## Provided Quants
39
+
40
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
41
+
42
+ | Link | Type | Size/GB | Notes |
43
+ |:-----|:-----|--------:|:------|
44
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate |
45
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.5 | mostly desperate |
46
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.6 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.6 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.6 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.7 | very low quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.7 | lower quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q2_K.gguf) | i1-Q2_K | 0.7 | IQ3_XXS probably better |
53
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.7 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.7 | IQ3_XS probably better |
55
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_S.gguf) | i1-IQ3_S | 0.7 | beats Q3_K* |
56
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_M.gguf) | i1-IQ3_M | 0.8 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.8 | IQ3_S probably better |
58
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.8 | IQ3_M probably better |
59
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.8 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.9 | prefer IQ4_XS |
61
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_0.gguf) | i1-Q4_0 | 0.9 | fast, low quality |
62
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.9 | optimal size/speed/quality |
63
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.9 | fast, recommended |
64
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_1.gguf) | i1-Q4_1 | 0.9 | |
65
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.0 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.0 | |
67
+ | [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q6_K.gguf) | i1-Q6_K | 1.1 | practically like static Q6_K |
68
+
69
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
70
+ types (lower is better):
71
+
72
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
73
+
74
+ And here are Artefact2's thoughts on the matter:
75
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
76
+
77
+ ## FAQ / Model Request
78
+
79
+ See https://huggingface.co/mradermacher/model_requests for some answers to
80
+ questions you might have and/or if you want some other model quantized.
81
+
82
+ ## Thanks
83
+
84
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
85
+ me use its servers and providing upgrades to my workstation to enable
86
+ 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.
87
+
88
+ <!-- end -->