auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,7 @@ tags:
|
|
| 18 |
weighted/imatrix quants of https://huggingface.co/terrycraddock/Reflection-Llama-3.1-8B
|
| 19 |
|
| 20 |
<!-- provided-files -->
|
|
|
|
| 21 |
## Usage
|
| 22 |
|
| 23 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
@@ -30,27 +31,27 @@ more details, including on how to concatenate multi-part files.
|
|
| 30 |
|
| 31 |
| Link | Type | Size/GB | Notes |
|
| 32 |
|:-----|:-----|--------:|:------|
|
| 33 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 34 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 35 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 36 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 37 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 38 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 39 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 40 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 41 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 42 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 43 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 44 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 45 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 46 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 47 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 48 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 49 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 50 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 51 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 52 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 53 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 54 |
|
| 55 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 56 |
types (lower is better):
|
|
|
|
| 18 |
weighted/imatrix quants of https://huggingface.co/terrycraddock/Reflection-Llama-3.1-8B
|
| 19 |
|
| 20 |
<!-- provided-files -->
|
| 21 |
+
static quants are available at https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF
|
| 22 |
## Usage
|
| 23 |
|
| 24 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
|
| 31 |
|
| 32 |
| Link | Type | Size/GB | Notes |
|
| 33 |
|:-----|:-----|--------:|:------|
|
| 34 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-IQ1_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 4.1 | for the desperate |
|
| 35 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-IQ1_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 4.4 | mostly desperate |
|
| 36 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-IQ2_XXS.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.9 | |
|
| 37 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-IQ2_XS.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 5.3 | |
|
| 38 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-IQ2_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 5.6 | |
|
| 39 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-IQ2_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 6.0 | |
|
| 40 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-Q2_K.gguf) | i1-Q2_K | 6.5 | IQ3_XXS probably better |
|
| 41 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-IQ3_XXS.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.6 | lower quality |
|
| 42 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-IQ3_XS.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 7.1 | |
|
| 43 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-Q3_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 7.4 | IQ3_XS probably better |
|
| 44 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-IQ3_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 7.5 | beats Q3_K* |
|
| 45 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-IQ3_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 7.7 | |
|
| 46 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-Q3_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 8.1 | IQ3_S probably better |
|
| 47 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-Q3_K_L.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.7 | IQ3_M probably better |
|
| 48 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-IQ4_XS.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 9.0 | |
|
| 49 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-Q4_0.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-Q4_0.gguf) | i1-Q4_0 | 9.5 | fast, low quality |
|
| 50 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 9.5 | optimal size/speed/quality |
|
| 51 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-Q4_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.9 | fast, recommended |
|
| 52 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-Q5_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 11.3 | |
|
| 53 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-Q5_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 11.6 | |
|
| 54 |
+
| [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/Reflection-Llama-3.1-8B.i1-Q6_K.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF/resolve/main/reflection-llama-3.1-8B.i1-Q6_K.gguf) | i1-Q6_K | 13.3 | practically like static Q6_K |
|
| 55 |
|
| 56 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 57 |
types (lower is better):
|