Update README.md
Browse files
README.md
CHANGED
|
@@ -188,10 +188,12 @@ extra_gated_button_content: Submit
|
|
| 188 |
quantized_by: bartowski
|
| 189 |
---
|
| 190 |
|
| 191 |
-
## Llamacpp imatrix Quantizations of Meta-Llama-3-8B-Instruct
|
| 192 |
|
| 193 |
<b>This conversion is based on the merged Llama 3 support in llama.cpp (release b2710)</b>
|
| 194 |
|
|
|
|
|
|
|
| 195 |
### Known working on:
|
| 196 |
- LM Studio 0.2.20*
|
| 197 |
- koboldcpp 1.63
|
|
@@ -227,28 +229,28 @@ All quants made using imatrix option with dataset provided by Kalomaze [here](ht
|
|
| 227 |
|
| 228 |
| Filename | Quant type | File Size | Description |
|
| 229 |
| -------- | ---------- | --------- | ----------- |
|
| 230 |
-
| [Meta-Llama-3-8B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
|
| 231 |
-
| [Meta-Llama-3-8B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
|
| 232 |
-
| [Meta-Llama-3-8B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
|
| 233 |
-
| [Meta-Llama-3-8B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
|
| 234 |
-
| [Meta-Llama-3-8B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
|
| 235 |
-
| [Meta-Llama-3-8B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
|
| 236 |
-
| [Meta-Llama-3-8B-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ4_NL.gguf) | IQ4_NL | 4.67GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
|
| 237 |
-
| [Meta-Llama-3-8B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
| 238 |
-
| [Meta-Llama-3-8B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
|
| 239 |
-
| [Meta-Llama-3-8B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
|
| 240 |
-
| [Meta-Llama-3-8B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
| 241 |
-
| [Meta-Llama-3-8B-Instruct-IQ3_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ3_S.gguf) | IQ3_S | 3.68GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
|
| 242 |
-
| [Meta-Llama-3-8B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
|
| 243 |
-
| [Meta-Llama-3-8B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
| 244 |
-
| [Meta-Llama-3-8B-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
| 245 |
-
| [Meta-Llama-3-8B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
|
| 246 |
-
| [Meta-Llama-3-8B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
|
| 247 |
-
| [Meta-Llama-3-8B-Instruct-IQ2_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
|
| 248 |
-
| [Meta-Llama-3-8B-Instruct-IQ2_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
|
| 249 |
-
| [Meta-Llama-3-8B-Instruct-IQ2_XXS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ2_XXS.gguf) | IQ2_XXS | 2.39GB | Lower quality, uses SOTA techniques to be usable. |
|
| 250 |
-
| [Meta-Llama-3-8B-Instruct-IQ1_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ1_M.gguf) | IQ1_M | 2.16GB | Extremely low quality, *not* recommended. |
|
| 251 |
-
| [Meta-Llama-3-8B-Instruct-IQ1_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ1_S.gguf) | IQ1_S | 2.01GB | Extremely low quality, *not* recommended. |
|
| 252 |
|
| 253 |
## Which file should I choose?
|
| 254 |
|
|
|
|
| 188 |
quantized_by: bartowski
|
| 189 |
---
|
| 190 |
|
| 191 |
+
## Llamacpp imatrix Quantizations of Meta-Llama-3-8B-Instruct (old)
|
| 192 |
|
| 193 |
<b>This conversion is based on the merged Llama 3 support in llama.cpp (release b2710)</b>
|
| 194 |
|
| 195 |
+
# This model is being deprecated in favour of the incoming conversion/quant with BPE tokenizers fixed. Will be here: https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF
|
| 196 |
+
|
| 197 |
### Known working on:
|
| 198 |
- LM Studio 0.2.20*
|
| 199 |
- koboldcpp 1.63
|
|
|
|
| 229 |
|
| 230 |
| Filename | Quant type | File Size | Description |
|
| 231 |
| -------- | ---------- | --------- | ----------- |
|
| 232 |
+
| [Meta-Llama-3-8B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
|
| 233 |
+
| [Meta-Llama-3-8B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
|
| 234 |
+
| [Meta-Llama-3-8B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
|
| 235 |
+
| [Meta-Llama-3-8B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
|
| 236 |
+
| [Meta-Llama-3-8B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
|
| 237 |
+
| [Meta-Llama-3-8B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
|
| 238 |
+
| [Meta-Llama-3-8B-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ4_NL.gguf) | IQ4_NL | 4.67GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
|
| 239 |
+
| [Meta-Llama-3-8B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
| 240 |
+
| [Meta-Llama-3-8B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
|
| 241 |
+
| [Meta-Llama-3-8B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
|
| 242 |
+
| [Meta-Llama-3-8B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
| 243 |
+
| [Meta-Llama-3-8B-Instruct-IQ3_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ3_S.gguf) | IQ3_S | 3.68GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
|
| 244 |
+
| [Meta-Llama-3-8B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
|
| 245 |
+
| [Meta-Llama-3-8B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
| 246 |
+
| [Meta-Llama-3-8B-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
| 247 |
+
| [Meta-Llama-3-8B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
|
| 248 |
+
| [Meta-Llama-3-8B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
|
| 249 |
+
| [Meta-Llama-3-8B-Instruct-IQ2_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
|
| 250 |
+
| [Meta-Llama-3-8B-Instruct-IQ2_XS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
|
| 251 |
+
| [Meta-Llama-3-8B-Instruct-IQ2_XXS.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ2_XXS.gguf) | IQ2_XXS | 2.39GB | Lower quality, uses SOTA techniques to be usable. |
|
| 252 |
+
| [Meta-Llama-3-8B-Instruct-IQ1_M.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ1_M.gguf) | IQ1_M | 2.16GB | Extremely low quality, *not* recommended. |
|
| 253 |
+
| [Meta-Llama-3-8B-Instruct-IQ1_S.gguf](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-old-GGUF/blob/main/Meta-Llama-3-8B-Instruct-IQ1_S.gguf) | IQ1_S | 2.01GB | Extremely low quality, *not* recommended. |
|
| 254 |
|
| 255 |
## Which file should I choose?
|
| 256 |
|