mradermacher
commited on
Commit
•
fe12d1f
1
Parent(s):
d9c8183
auto-patch README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ quantized_by: mradermacher
|
|
16 |
static quants of https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
|
17 |
|
18 |
<!-- provided-files -->
|
19 |
-
weighted/imatrix quants
|
20 |
## Usage
|
21 |
|
22 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -30,8 +30,20 @@ more details, including on how to concatenate multi-part files.
|
|
30 |
| Link | Type | Size/GB | Notes |
|
31 |
|:-----|:-----|--------:|:------|
|
32 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.Q2_K.gguf) | Q2_K | 3.3 | |
|
|
|
|
|
33 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
|
|
|
|
|
|
|
|
|
34 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
|
36 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
37 |
types (lower is better):
|
|
|
16 |
static quants of https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
|
17 |
|
18 |
<!-- provided-files -->
|
19 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-i1-GGUF
|
20 |
## Usage
|
21 |
|
22 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
30 |
| Link | Type | Size/GB | Notes |
|
31 |
|:-----|:-----|--------:|:------|
|
32 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.Q2_K.gguf) | Q2_K | 3.3 | |
|
33 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
|
34 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
|
35 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.IQ3_M.gguf) | IQ3_M | 3.9 | |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF/resolve/main/Llama-3.1-8B-Lexi-Uncensored-V2.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
|
47 |
|
48 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
49 |
types (lower is better):
|