Hugging Face's logo

mradermacher
/
Medmerge-tulu-70b-i1-GGUF

Transformers
GGUF
English
Merge
mergekit
epfl-llm/meditron-70b
allenai/tulu-2-dpo-70b
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
2bad7f7
•
1 Parent(s): 3922337

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -42,14 +42,18 @@ more details, including on how to concatenate multi-part files.
42
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-IQ2_M.gguf) | i1-IQ2_M | 23.3 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |
 
 
45
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-IQ3_M.gguf) | i1-IQ3_M | 31.0 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.2 | IQ3_M probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 36.9 | |
 
50
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.5 | fast, recommended |
52
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.6 | |
 
53
  | [PART 1](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 56.7 | practically like static Q6_K |
54
 
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
42
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-IQ2_M.gguf) | i1-IQ2_M | 23.3 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q2_K.gguf) | i1-Q2_K | 25.6 | IQ3_XXS probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 26.7 | lower quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 28.4 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-IQ3_S.gguf) | i1-IQ3_S | 30.0 | beats Q3_K* |
47
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.0 | IQ3_XS probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-IQ3_M.gguf) | i1-IQ3_M | 31.0 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.4 | IQ3_S probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 36.2 | IQ3_M probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 36.9 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q4_0.gguf) | i1-Q4_0 | 39.1 | fast, low quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.3 | optimal size/speed/quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.5 | fast, recommended |
55
  | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 47.6 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 48.9 | |
57
  | [PART 1](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Medmerge-tulu-70b-i1-GGUF/resolve/main/Medmerge-tulu-70b.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 56.7 | practically like static Q6_K |
58
 
59
  Here is a handy graph by ikawrakow comparing some lower-quality quant