Commit
•
00c1e25
1
Parent(s):
6155759
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -34,7 +34,7 @@ more details, including on how to concatenate multi-part files.
|
|
| 34 |
| Link | Type | Size/GB | Notes |
|
| 35 |
|:-----|:-----|--------:|:------|
|
| 36 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
|
| 37 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 |
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
|
|
@@ -55,7 +55,6 @@ more details, including on how to concatenate multi-part files.
|
|
| 55 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
|
| 56 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
|
| 57 |
|
| 58 |
-
|
| 59 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 60 |
types (lower is better):
|
| 61 |
|
|
|
|
| 34 |
| Link | Type | Size/GB | Notes |
|
| 35 |
|:-----|:-----|--------:|:------|
|
| 36 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
|
| 37 |
+
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
|
|
|
|
| 55 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
|
| 56 |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Ultra-Instruct-i1-GGUF/resolve/main/Llama-3-8B-Ultra-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
|
| 57 |
|
|
|
|
| 58 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 59 |
types (lower is better):
|
| 60 |
|