Hugging Face's logo

mradermacher
/
NeuralTrixlaser-bf16-GGUF

Transformers
GGUF
English
Merge
mergekit
lazymergekit
bardsai/jaskier-7b-dpo-v3.3
Kquant03/NeuralTrix-7B-dpo-laser
CultriX/NeuralTrix-v4-bf16
CultriX/NeuralTrix-V2
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
a1c20a2
·
verified ·
1 Parent(s): 36b5a13

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -41,10 +41,14 @@ more details, including on how to concatenate multi-part files.
41
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
42
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
 
44
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
45
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
 
 
46
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
47
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
 
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):
 
41
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
42
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
43
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
45
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
46
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
49
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
50
  | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/NeuralTrixlaser-bf16-GGUF/resolve/main/NeuralTrixlaser-bf16.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):