auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -21,8 +21,8 @@ tags:
|
|
| 21 |
<!-- ### vocab_type: -->
|
| 22 |
static quants of https://huggingface.co/McGill-NLP/Llama-3-8B-Web
|
| 23 |
|
| 24 |
-
|
| 25 |
<!-- provided-files -->
|
|
|
|
| 26 |
## Usage
|
| 27 |
|
| 28 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
@@ -35,21 +35,21 @@ more details, including on how to concatenate multi-part files.
|
|
| 35 |
|
| 36 |
| Link | Type | Size/GB | Notes |
|
| 37 |
|:-----|:-----|--------:|:------|
|
| 38 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 39 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 40 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 41 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 42 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 43 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 44 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 45 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 46 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 47 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 48 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 49 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 50 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 51 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 52 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-
|
| 53 |
|
| 54 |
|
| 55 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
|
| 21 |
<!-- ### vocab_type: -->
|
| 22 |
static quants of https://huggingface.co/McGill-NLP/Llama-3-8B-Web
|
| 23 |
|
|
|
|
| 24 |
<!-- provided-files -->
|
| 25 |
+
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
|
| 26 |
## Usage
|
| 27 |
|
| 28 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
|
| 35 |
|
| 36 |
| Link | Type | Size/GB | Notes |
|
| 37 |
|:-----|:-----|--------:|:------|
|
| 38 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.Q2_K.gguf) | Q2_K | 3.3 | |
|
| 39 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
|
| 40 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
|
| 41 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
|
| 42 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.IQ3_M.gguf) | IQ3_M | 3.9 | |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
|
| 44 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
|
| 45 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
|
| 46 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
|
| 47 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
|
| 48 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
|
| 49 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
|
| 50 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
|
| 51 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
|
| 52 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Web-GGUF/resolve/main/Llama-3-8B-Web.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
|
| 53 |
|
| 54 |
|
| 55 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|