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
5f8e5f5
·
verified ·
1 Parent(s): d54ba34

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -41,8 +41,10 @@ more details, including on how to concatenate multi-part files.
41
  | [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 | |
42
  | [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 |
43
  | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ3_XXS.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ3_XXS.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ3_XXS.gguf.part3of3) | i1-IQ3_XXS | 132.2 | lower quality |
 
44
  | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q3_K_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q3_K_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q3_K_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q3_K_M.gguf.part4of4) | i1-Q3_K_M | 171.6 | IQ3_S probably better |
45
  | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_S.gguf.part4of4) | i1-Q4_K_S | 195.2 | optimal size/speed/quality |
 
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):
 
41
  | [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 | |
42
  | [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 |
43
  | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ3_XXS.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ3_XXS.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ3_XXS.gguf.part3of3) | i1-IQ3_XXS | 132.2 | lower quality |
44
+ | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ3_XS.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ3_XS.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-IQ3_XS.gguf.part3of3) | i1-IQ3_XS | 142.6 | |
45
  | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q3_K_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q3_K_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q3_K_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q3_K_M.gguf.part4of4) | i1-Q3_K_M | 171.6 | IQ3_S probably better |
46
  | [PART 1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_S.gguf.part4of4) | i1-Q4_K_S | 195.2 | optimal size/speed/quality |
47
+ | [P1](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_M.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_M.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_M.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_M.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Nemotron-4-340B-Instruct-hf-i1-GGUF/resolve/main/Nemotron-4-340B-Instruct-hf.i1-Q4_K_M.gguf.part5of5) | i1-Q4_K_M | 210.3 | fast, recommended |
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):