Hugging Face's logo

mradermacher
/
Maestro-R1-Llama-8B-GGUF

Transformers
GGUF
English
unsloth
trl
sft
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
9e324cf
·
verified ·
1 Parent(s): acbe066

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -22,7 +22,7 @@ tags:
22
  static quants of https://huggingface.co/suayptalha/Maestro-R1-Llama-8B
23
 
24
  <!-- provided-files -->
25
- weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
26
  ## Usage
27
 
28
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -39,9 +39,14 @@ more details, including on how to concatenate multi-part files.
39
  | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
 
42
  | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
 
 
 
43
  | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
 
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
47
  types (lower is better):
 
22
  static quants of https://huggingface.co/suayptalha/Maestro-R1-Llama-8B
23
 
24
  <!-- provided-files -->
25
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-i1-GGUF
26
  ## Usage
27
 
28
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
39
  | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
43
  | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
44
+ | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
45
+ | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
47
  | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/Maestro-R1-Llama-8B-GGUF/resolve/main/Maestro-R1-Llama-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):