Transformers
GGUF
English
mergekit
Merge
alpaca
mistral
Not-For-All-Audiences
nsfw
Inference Endpoints
conversational
mradermacher
commited on
Commit
•
e37e4ca
1
Parent(s):
442c347
auto-patch README.md
Browse files
README.md
CHANGED
@@ -41,14 +41,13 @@ more details, including on how to concatenate multi-part files.
|
|
41 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
|
44 |
-
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.IQ4_NL.gguf) | IQ4_NL | 4.4 |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
|
46 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
|
48 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
|
49 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
|
50 |
|
51 |
-
|
52 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
53 |
types (lower is better):
|
54 |
|
|
|
41 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q4_0.gguf) | Q4_0 | 4.4 | fast, low quality |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.IQ4_NL.gguf) | IQ4_NL | 4.4 | prefer IQ4_XS |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
|
46 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
|
48 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
|
49 |
| [GGUF](https://huggingface.co/mradermacher/IceTeaRP-7b-GGUF/resolve/main/IceTeaRP-7b.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
|
50 |
|
|
|
51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
52 |
types (lower is better):
|
53 |
|