bartowski commited on
Commit
af129e3
1 Parent(s): 0217160

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -3
README.md CHANGED
@@ -179,15 +179,17 @@ All quants made using imatrix option with dataset from [here](https://gist.githu
179
 
180
  | Filename | Quant type | File Size | Description |
181
  | -------- | ---------- | --------- | ----------- |
 
182
  | [Replete-Coder-Qwen-1.5b-Q8_0.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q8_0.gguf) | Q8_0 | 1646.57MB | Extremely high quality, generally unneeded but max available quant. |
 
183
  | [Replete-Coder-Qwen-1.5b-Q6_K.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q6_K.gguf) | Q6_K | 1272.73MB | Very high quality, near perfect, *recommended*. |
 
184
  | [Replete-Coder-Qwen-1.5b-Q5_K_M.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q5_K_M.gguf) | Q5_K_M | 1125.04MB | High quality, *recommended*. |
185
- | [Replete-Coder-Qwen-1.5b-Q5_K_S.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF//main/Replete-Coder-Qwen-1.5b-Q5_K_S.gguf) | Q5_K_S | | High quality, *recommended*. |
186
  | [Replete-Coder-Qwen-1.5b-Q4_K_M.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q4_K_M.gguf) | Q4_K_M | 986.04MB | Good quality, uses about 4.83 bits per weight, *recommended*. |
187
- | [Replete-Coder-Qwen-1.5b-Q4_K_S.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF//main/Replete-Coder-Qwen-1.5b-Q4_K_S.gguf) | Q4_K_S | | Slightly lower quality with more space savings, *recommended*. |
188
  | [Replete-Coder-Qwen-1.5b-IQ4_XS.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-IQ4_XS.gguf) | IQ4_XS | 895.72MB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
 
189
  | [Replete-Coder-Qwen-1.5b-Q3_K_L.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q3_K_L.gguf) | Q3_K_L | 880.16MB | Lower quality but usable, good for low RAM availability. |
190
- | [Replete-Coder-Qwen-1.5b-IQ3_M.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF//main/Replete-Coder-Qwen-1.5b-IQ3_M.gguf) | IQ3_M | | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
191
 
192
  ## Downloading using huggingface-cli
193
 
 
179
 
180
  | Filename | Quant type | File Size | Description |
181
  | -------- | ---------- | --------- | ----------- |
182
+ | [Replete-Coder-Qwen-1.5b-Q8_0_L.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q8_0_L.gguf) | Q8_0_L | 1870.00MB | Experimental, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
183
  | [Replete-Coder-Qwen-1.5b-Q8_0.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q8_0.gguf) | Q8_0 | 1646.57MB | Extremely high quality, generally unneeded but max available quant. |
184
+ | [Replete-Coder-Qwen-1.5b-Q6_K_L.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q6_K_L.gguf) | Q6_K_L | 1550MB | Experimental, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. |
185
  | [Replete-Coder-Qwen-1.5b-Q6_K.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q6_K.gguf) | Q6_K | 1272.73MB | Very high quality, near perfect, *recommended*. |
186
+ | [Replete-Coder-Qwen-1.5b-Q5_K_L.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q5_K_L.gguf) | Q5_K_L | 1400MB | Experimental, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, *recommended*. |
187
  | [Replete-Coder-Qwen-1.5b-Q5_K_M.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q5_K_M.gguf) | Q5_K_M | 1125.04MB | High quality, *recommended*. |
188
+ | [Replete-Coder-Qwen-1.5b-Q4_K_L.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q4_K_L.gguf) | Q4_K_L | 1260MB | Experimental, uses f16 for embed and output weights. Please provide any feedback of differences. Good quality, uses about 4.83 bits per weight, *recommended*. |
189
  | [Replete-Coder-Qwen-1.5b-Q4_K_M.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q4_K_M.gguf) | Q4_K_M | 986.04MB | Good quality, uses about 4.83 bits per weight, *recommended*. |
 
190
  | [Replete-Coder-Qwen-1.5b-IQ4_XS.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-IQ4_XS.gguf) | IQ4_XS | 895.72MB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
191
+ | [Replete-Coder-Qwen-1.5b-Q3_K_XL.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q3_K_XL.gguf) | Q3_K_XL | 1160MB | Experimental, uses f16 for embed and output weights. Please provide any feedback of differences. Lower quality but usable, good for low RAM availability. |
192
  | [Replete-Coder-Qwen-1.5b-Q3_K_L.gguf](https://huggingface.co/bartowski/Replete-Coder-Qwen-1.5b-GGUF/blob/main/Replete-Coder-Qwen-1.5b-Q3_K_L.gguf) | Q3_K_L | 880.16MB | Lower quality but usable, good for low RAM availability. |
 
193
 
194
  ## Downloading using huggingface-cli
195