Hugging Face's logo

mradermacher
/
Triangulum-10B-it-GGUF

Transformers
GGUF
triangulum_10b
sft
chain_of_thought
ollama
text-generation-inference
llama_for_causal_lm
reasoning
CoT
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
f52f0f3
·
verified ·
1 Parent(s): 264ba69

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -1
README.md CHANGED
@@ -32,7 +32,7 @@ tags:
32
  static quants of https://huggingface.co/prithivMLmods/Triangulum-10B-it
33
 
34
  <!-- provided-files -->
35
- weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
36
  ## Usage
37
 
38
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -49,8 +49,14 @@ more details, including on how to concatenate multi-part files.
49
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q3_K_S.gguf) | Q3_K_S | 4.7 | |
50
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q3_K_M.gguf) | Q3_K_M | 5.2 | lower quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q3_K_L.gguf) | Q3_K_L | 5.6 | |
 
52
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q4_K_S.gguf) | Q4_K_S | 6.1 | fast, recommended |
 
 
 
53
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q6_K.gguf) | Q6_K | 8.6 | very good quality |
 
 
54
 
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant
56
  types (lower is better):
 
32
  static quants of https://huggingface.co/prithivMLmods/Triangulum-10B-it
33
 
34
  <!-- provided-files -->
35
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Triangulum-10B-it-i1-GGUF
36
  ## Usage
37
 
38
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
49
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q3_K_S.gguf) | Q3_K_S | 4.7 | |
50
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q3_K_M.gguf) | Q3_K_M | 5.2 | lower quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q3_K_L.gguf) | Q3_K_L | 5.6 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.IQ4_XS.gguf) | IQ4_XS | 5.8 | |
53
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q4_K_S.gguf) | Q4_K_S | 6.1 | fast, recommended |
54
+ | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q4_K_M.gguf) | Q4_K_M | 6.4 | fast, recommended |
55
+ | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q5_K_S.gguf) | Q5_K_S | 7.2 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q5_K_M.gguf) | Q5_K_M | 7.4 | |
57
  | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q6_K.gguf) | Q6_K | 8.6 | very good quality |
58
+ | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.Q8_0.gguf) | Q8_0 | 11.1 | fast, best quality |
59
+ | [GGUF](https://huggingface.co/mradermacher/Triangulum-10B-it-GGUF/resolve/main/Triangulum-10B-it.f16.gguf) | f16 | 20.7 | 16 bpw, overkill |
60
 
61
  Here is a handy graph by ikawrakow comparing some lower-quality quant
62
  types (lower is better):