Hugging Face's logo

mradermacher
/
NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF

Transformers
GGUF
English
distillation
synthetic data
function calling
structured outputs
json mode
imatrix
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
253052e
·
verified ·
1 Parent(s): fbbd4d1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -44,9 +44,11 @@ more details, including on how to concatenate multi-part files.
44
  | Link | Type | Size/GB | Notes |
45
  |:-----|:-----|--------:|:------|
46
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
 
47
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
48
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
49
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
 
50
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
51
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 24.6 | very low quality |
52
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
@@ -58,6 +60,8 @@ more details, including on how to concatenate multi-part files.
58
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 | |
59
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
60
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
 
 
61
  | [PART 1](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
62
 
63
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
44
  | Link | Type | Size/GB | Notes |
45
  |:-----|:-----|--------:|:------|
46
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
47
+ | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate |
48
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
49
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
50
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | |
52
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
53
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 24.6 | very low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
 
60
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 | |
61
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
62
  | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
63
+ | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 | |
65
  | [PART 1](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/NousResearch-Hermes-2-Theta-Llama-3-70B-i1-GGUF/resolve/main/NousResearch-Hermes-2-Theta-Llama-3-70B.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
66
 
67
  Here is a handy graph by ikawrakow comparing some lower-quality quant