Hugging Face's logo

mradermacher
/
T3qm7xNeuralsirkrishna_Experiment24Experiment26-GGUF

Transformers
GGUF
English
Safetensors
text-generation-inference
Merge
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
5b2c130
·
verified ·
1 Parent(s): 020db14

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -36,7 +36,14 @@ more details, including on how to concatenate multi-part files.
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
38
  | [GGUF](https://huggingface.co/mradermacher/T3qm7xNeuralsirkrishna_Experiment24Experiment26-GGUF/resolve/main/T3qm7xNeuralsirkrishna_Experiment24Experiment26.Q2_K.gguf) | Q2_K | 2.8 | |
 
 
 
39
  | [GGUF](https://huggingface.co/mradermacher/T3qm7xNeuralsirkrishna_Experiment24Experiment26-GGUF/resolve/main/T3qm7xNeuralsirkrishna_Experiment24Experiment26.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
 
 
 
 
40
 
41
  Here is a handy graph by ikawrakow comparing some lower-quality quant
42
  types (lower is better):
 
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
38
  | [GGUF](https://huggingface.co/mradermacher/T3qm7xNeuralsirkrishna_Experiment24Experiment26-GGUF/resolve/main/T3qm7xNeuralsirkrishna_Experiment24Experiment26.Q2_K.gguf) | Q2_K | 2.8 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/T3qm7xNeuralsirkrishna_Experiment24Experiment26-GGUF/resolve/main/T3qm7xNeuralsirkrishna_Experiment24Experiment26.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/T3qm7xNeuralsirkrishna_Experiment24Experiment26-GGUF/resolve/main/T3qm7xNeuralsirkrishna_Experiment24Experiment26.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
41
+ | [GGUF](https://huggingface.co/mradermacher/T3qm7xNeuralsirkrishna_Experiment24Experiment26-GGUF/resolve/main/T3qm7xNeuralsirkrishna_Experiment24Experiment26.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
42
  | [GGUF](https://huggingface.co/mradermacher/T3qm7xNeuralsirkrishna_Experiment24Experiment26-GGUF/resolve/main/T3qm7xNeuralsirkrishna_Experiment24Experiment26.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/T3qm7xNeuralsirkrishna_Experiment24Experiment26-GGUF/resolve/main/T3qm7xNeuralsirkrishna_Experiment24Experiment26.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
44
+ | [GGUF](https://huggingface.co/mradermacher/T3qm7xNeuralsirkrishna_Experiment24Experiment26-GGUF/resolve/main/T3qm7xNeuralsirkrishna_Experiment24Experiment26.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/T3qm7xNeuralsirkrishna_Experiment24Experiment26-GGUF/resolve/main/T3qm7xNeuralsirkrishna_Experiment24Experiment26.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/T3qm7xNeuralsirkrishna_Experiment24Experiment26-GGUF/resolve/main/T3qm7xNeuralsirkrishna_Experiment24Experiment26.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):