Hugging Face's logo

mradermacher
/
Llama-3.3-70B-o1-i1-GGUF

Transformers
GGUF
English
text-generation-inference
unsloth
llama
trl
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
f74bda3
·
verified ·
1 Parent(s): ba610fd

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -47,14 +47,19 @@ more details, including on how to concatenate multi-part files.
47
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 24.6 | very low quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
 
 
50
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
52
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
53
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 37.2 | IQ3_M probably better |
54
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 | |
 
55
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
56
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
 
57
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | |
 
58
  | [PART 1](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
59
 
60
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
47
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 24.6 | very low quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-IQ3_S.gguf) | i1-IQ3_S | 31.0 | beats Q3_K* |
52
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
53
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
54
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
55
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 37.2 | IQ3_M probably better |
56
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q4_0.gguf) | i1-Q4_0 | 40.2 | fast, low quality |
58
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
59
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
60
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q4_1.gguf) | i1-Q4_1 | 44.4 | |
61
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | |
62
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 | |
63
  | [PART 1](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3.3-70B-o1-i1-GGUF/resolve/main/Llama-3.3-70B-o1.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
64
 
65
  Here is a handy graph by ikawrakow comparing some lower-quality quant