Hugging Face's logo

mradermacher
/
megatron_v3_2x7B-GGUF

Transformers
GGUF
English
Turkish
Mixture of Experts
Merge
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
bc9f1f5
•
1 Parent(s): 27e42e7

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -2,6 +2,7 @@
2
  base_model: Eurdem/megatron_v3_2x7B
3
  language:
4
  - en
 
5
  library_name: transformers
6
  license: apache-2.0
7
  quantized_by: mradermacher
@@ -37,14 +38,13 @@ more details, including on how to concatenate multi-part files.
37
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.IQ4_XS.gguf) | IQ4_XS | 7.2 | |
38
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q4_0.gguf) | Q4_0 | 7.5 | fast, low quality |
39
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q4_K_S.gguf) | Q4_K_S | 7.6 | fast, recommended |
40
- | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.IQ4_NL.gguf) | IQ4_NL | 7.6 | slightly worse than Q4_K_S |
41
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q4_K_M.gguf) | Q4_K_M | 8.0 | fast, recommended |
42
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q5_K_S.gguf) | Q5_K_S | 9.1 | |
43
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q5_K_M.gguf) | Q5_K_M | 9.4 | |
44
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q6_K.gguf) | Q6_K | 10.8 | very good quality |
45
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q8_0.gguf) | Q8_0 | 13.9 | fast, best quality |
46
 
47
-
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):
50
 
 
2
  base_model: Eurdem/megatron_v3_2x7B
3
  language:
4
  - en
5
+ - tr
6
  library_name: transformers
7
  license: apache-2.0
8
  quantized_by: mradermacher
 
38
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.IQ4_XS.gguf) | IQ4_XS | 7.2 | |
39
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q4_0.gguf) | Q4_0 | 7.5 | fast, low quality |
40
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q4_K_S.gguf) | Q4_K_S | 7.6 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.IQ4_NL.gguf) | IQ4_NL | 7.6 | prefer IQ4_XS |
42
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q4_K_M.gguf) | Q4_K_M | 8.0 | fast, recommended |
43
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q5_K_S.gguf) | Q5_K_S | 9.1 | |
44
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q5_K_M.gguf) | Q5_K_M | 9.4 | |
45
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q6_K.gguf) | Q6_K | 10.8 | very good quality |
46
  | [GGUF](https://huggingface.co/mradermacher/megatron_v3_2x7B-GGUF/resolve/main/megatron_v3_2x7B.Q8_0.gguf) | Q8_0 | 13.9 | fast, best quality |
47
 
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):
50