Upload README.md
Browse files
README.md
CHANGED
@@ -115,14 +115,11 @@ Refer to the Provided Files table below to see what files use which methods, and
|
|
115 |
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|
116 |
| ---- | ---- | ---- | ---- | ---- | ----- |
|
117 |
| [synthia-moe-v3-mixtral-8x7b.Q2_K.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q2_K.gguf) | Q2_K | 2 | 15.64 GB| 18.14 GB | smallest, significant quality loss - not recommended for most purposes |
|
118 |
-
| [synthia-moe-v3-mixtral-8x7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q3_K_S.gguf) | Q3_K_S | 3 | 20.29 GB| 22.79 GB | very small, high quality loss |
|
119 |
| [synthia-moe-v3-mixtral-8x7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q3_K_M.gguf) | Q3_K_M | 3 | 20.36 GB| 22.86 GB | very small, high quality loss |
|
120 |
| [synthia-moe-v3-mixtral-8x7b.Q4_0.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q4_0.gguf) | Q4_0 | 4 | 26.44 GB| 28.94 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
121 |
| [synthia-moe-v3-mixtral-8x7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q4_K_M.gguf) | Q4_K_M | 4 | 26.44 GB| 28.94 GB | medium, balanced quality - recommended |
|
122 |
-
| [synthia-moe-v3-mixtral-8x7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q4_K_S.gguf) | Q4_K_S | 4 | 26.44 GB| 28.94 GB | small, greater quality loss |
|
123 |
| [synthia-moe-v3-mixtral-8x7b.Q5_0.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q5_0.gguf) | Q5_0 | 5 | 32.23 GB| 34.73 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
124 |
| [synthia-moe-v3-mixtral-8x7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q5_K_M.gguf) | Q5_K_M | 5 | 32.23 GB| 34.73 GB | large, very low quality loss - recommended |
|
125 |
-
| [synthia-moe-v3-mixtral-8x7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q5_K_S.gguf) | Q5_K_S | 5 | 32.23 GB| 34.73 GB | large, low quality loss - recommended |
|
126 |
| [synthia-moe-v3-mixtral-8x7b.Q6_K.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q6_K.gguf) | Q6_K | 6 | 38.38 GB| 40.88 GB | very large, extremely low quality loss |
|
127 |
| [synthia-moe-v3-mixtral-8x7b.Q8_0.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q8_0.gguf) | Q8_0 | 8 | 49.62 GB| 52.12 GB | very large, extremely low quality loss - not recommended |
|
128 |
|
|
|
115 |
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|
116 |
| ---- | ---- | ---- | ---- | ---- | ----- |
|
117 |
| [synthia-moe-v3-mixtral-8x7b.Q2_K.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q2_K.gguf) | Q2_K | 2 | 15.64 GB| 18.14 GB | smallest, significant quality loss - not recommended for most purposes |
|
|
|
118 |
| [synthia-moe-v3-mixtral-8x7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q3_K_M.gguf) | Q3_K_M | 3 | 20.36 GB| 22.86 GB | very small, high quality loss |
|
119 |
| [synthia-moe-v3-mixtral-8x7b.Q4_0.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q4_0.gguf) | Q4_0 | 4 | 26.44 GB| 28.94 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
120 |
| [synthia-moe-v3-mixtral-8x7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q4_K_M.gguf) | Q4_K_M | 4 | 26.44 GB| 28.94 GB | medium, balanced quality - recommended |
|
|
|
121 |
| [synthia-moe-v3-mixtral-8x7b.Q5_0.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q5_0.gguf) | Q5_0 | 5 | 32.23 GB| 34.73 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
122 |
| [synthia-moe-v3-mixtral-8x7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q5_K_M.gguf) | Q5_K_M | 5 | 32.23 GB| 34.73 GB | large, very low quality loss - recommended |
|
|
|
123 |
| [synthia-moe-v3-mixtral-8x7b.Q6_K.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q6_K.gguf) | Q6_K | 6 | 38.38 GB| 40.88 GB | very large, extremely low quality loss |
|
124 |
| [synthia-moe-v3-mixtral-8x7b.Q8_0.gguf](https://huggingface.co/TheBloke/Synthia-MoE-v3-Mixtral-8x7B-GGUF/blob/main/synthia-moe-v3-mixtral-8x7b.Q8_0.gguf) | Q8_0 | 8 | 49.62 GB| 52.12 GB | very large, extremely low quality loss - not recommended |
|
125 |
|