Files changed (1) hide show
  1. README.md +10 -7
README.md CHANGED
@@ -215,13 +215,16 @@ Original model: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
215
  ## Available sizes
216
 
217
 
218
- | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
219
- | ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
220
- | [8_0](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-tokens-exl2/tree/8_0) | 8.0 | 8.0 | 8.4 GB | 9.8 GB | 11.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
221
- | [6_5](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-tokens-exl2/tree/6_5) | 6.5 | 8.0 | 7.2 GB | 8.6 GB | 10.6 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
222
- | [5_0](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-tokens-exl2/tree/5_0) | 5.0 | 6.0 | 6.0 GB | 7.4 GB | 9.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
223
- | [4_25](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-tokens-exl2/tree/4_25) | 4.25 | 6.0 | 5.3 GB | 6.7 GB | 8.7 GB | GPTQ equivalent bits per weight, slightly higher quality. |
224
- | [3_5](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-tokens-exl2/tree/3_5) | 3.5 | 6.0 | 4.7 GB | 6.1 GB | 8.1 GB | Lower quality, only use if you have to. |
 
 
 
225
 
226
  ## Download instructions
227
 
 
215
  ## Available sizes
216
 
217
 
218
+ | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (8k) | VRAM (16k) | VRAM (32k) | Description |
219
+ | ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ |
220
+ | [8_0](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-tokens-exl2/tree/8_0) | 8.0 | 8.0 | 10.1 GB | 10.5 GB | 11.5 GB | 13.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
221
+ | [6_5](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-tokens-exl2/tree/6_5) | 6.5 | 8.0 | 8.9 GB | 9.3 GB | 10.3 GB | 12.4 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
222
+ | [5_0](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-tokens-exl2/tree/5_0) | 5.0 | 6.0 | 7.7 GB | 8.1 GB | 9.1 GB | 11.2 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
223
+ | [4_25](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-tokens-exl2/tree/4_25) | 4.25 | 6.0 | 7.0 GB | 7.4 GB | 8.4 GB | 10.5 GB | GPTQ equivalent bits per weight, slightly higher quality. |
224
+ | [3_5](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-special-tokens-exl2/tree/3_5) | 3.5 | 6.0 | 6.4 GB | 6.8 GB | 7.8 GB | 9.9 GB | Lower quality, only use if you have to. |
225
+
226
+
227
+ ## Download instructions
228
 
229
  ## Download instructions
230