Hugging Face's logo

mradermacher
/
Nemotron-4-340B-Instruct-hf-i1-GGUF

Transformers
English
vllm
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
482b438
·
verified ·
1 Parent(s): ebd2e6d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -36,6 +36,8 @@ more details, including on how to concatenate multi-part files.
36
  | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ1_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ1_S.gguf.part2of2) | i1-IQ1_S | 74.9 | for the desperate |
37
  | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ1_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ1_M.gguf.part2of2) | i1-IQ1_M | 81.5 | mostly desperate |
38
  | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_S.gguf.part3of3) | i1-IQ2_S | 108.9 | |
 
 
39
 
40
  Here is a handy graph by ikawrakow comparing some lower-quality quant
41
  types (lower is better):
 
36
  | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ1_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ1_S.gguf.part2of2) | i1-IQ1_S | 74.9 | for the desperate |
37
  | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ1_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ1_M.gguf.part2of2) | i1-IQ1_M | 81.5 | mostly desperate |
38
  | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_S.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_S.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_S.gguf.part3of3) | i1-IQ2_S | 108.9 | |
39
+ | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ2_M.gguf.part3of3) | i1-IQ2_M | 117.6 | |
40
+ | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q2_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q2_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q2_K.gguf.part3of3) | i1-Q2_K | 131.6 | IQ3_XXS probably better |
41
 
42
  Here is a handy graph by ikawrakow comparing some lower-quality quant
43
  types (lower is better):