Hugging Face's logo

mradermacher
/
Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF

Transformers
GGUF
English
nvidia
llama3.1
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
60e5cd6
·
verified ·
1 Parent(s): 41a934c

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -40,6 +40,7 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | |
42
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
 
43
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | |
@@ -52,6 +53,7 @@ more details, including on how to concatenate multi-part files.
52
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q4_0.gguf) | i1-Q4_0 | 40.2 | fast, low quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
 
55
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | |
56
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 | |
57
  | [PART 1](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
 
40
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | |
42
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q2_K_S.gguf) | i1-Q2_K_S | 24.6 | very low quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | |
 
53
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q4_0.gguf) | i1-Q4_0 | 40.2 | fast, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
55
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
56
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q4_1.gguf) | i1-Q4_1 | 44.4 | |
57
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | |
58
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 | |
59
  | [PART 1](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF/resolve/main/Llama-3.1-Nemotron-70B-Instruct-HF.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |