Hugging Face's logo

mradermacher
/
LLaMA3-Reasoning-GGUF

Transformers
GGUF
English
LLaMA3
llama
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
f5bf1a5
·
verified ·
1 Parent(s): bb55c73

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -35,6 +35,7 @@ more details, including on how to concatenate multi-part files.
35
  | [GGUF](https://huggingface.co/mradermacher/LLaMA3-Reasoning-GGUF/resolve/main/LLaMA3-Reasoning.Q2_K.gguf) | Q2_K | 0.2 | |
36
  | [GGUF](https://huggingface.co/mradermacher/LLaMA3-Reasoning-GGUF/resolve/main/LLaMA3-Reasoning.IQ3_S.gguf) | IQ3_S | 0.2 | beats Q3_K* |
37
  | [GGUF](https://huggingface.co/mradermacher/LLaMA3-Reasoning-GGUF/resolve/main/LLaMA3-Reasoning.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended |
 
38
  | [GGUF](https://huggingface.co/mradermacher/LLaMA3-Reasoning-GGUF/resolve/main/LLaMA3-Reasoning.f16.gguf) | f16 | 0.4 | 16 bpw, overkill |
39
 
40
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
35
  | [GGUF](https://huggingface.co/mradermacher/LLaMA3-Reasoning-GGUF/resolve/main/LLaMA3-Reasoning.Q2_K.gguf) | Q2_K | 0.2 | |
36
  | [GGUF](https://huggingface.co/mradermacher/LLaMA3-Reasoning-GGUF/resolve/main/LLaMA3-Reasoning.IQ3_S.gguf) | IQ3_S | 0.2 | beats Q3_K* |
37
  | [GGUF](https://huggingface.co/mradermacher/LLaMA3-Reasoning-GGUF/resolve/main/LLaMA3-Reasoning.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended |
38
+ | [GGUF](https://huggingface.co/mradermacher/LLaMA3-Reasoning-GGUF/resolve/main/LLaMA3-Reasoning.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality |
39
  | [GGUF](https://huggingface.co/mradermacher/LLaMA3-Reasoning-GGUF/resolve/main/LLaMA3-Reasoning.f16.gguf) | f16 | 0.4 | 16 bpw, overkill |
40
 
41
  Here is a handy graph by ikawrakow comparing some lower-quality quant