bartowski/Yi-Coder-9B-Chat-GGUF-torrent
bartowski/Yi-Coder-9B-Chat-GGUF · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
| Filename | Quant Type | File Size | Split | Description |
|---|---|---|---|---|
| Yi-Coder-9B-Chat-f16.gguf | f16 | 17.66GB | False | Full F16 weights. |
| Yi-Coder-9B-Chat-Q8_0.gguf | Q8_0 | 9.38GB | False | Extremely high quality, generally unneeded but max available quant. |
| Yi-Coder-9B-Chat-Q6_K_L.gguf | Q6_K_L | 7.37GB | False | Uses Q8_0 for embed and output weights. Very high quality, near perfect, recommended. |
| Yi-Coder-9B-Chat-Q6_K.gguf | Q6_K | 7.25GB | False | Very high quality, near perfect, recommended. |
| Yi-Coder-9B-Chat-Q5_K_L.gguf | Q5_K_L | 6.42GB | False | Uses Q8_0 for embed and output weights. High quality, recommended. |
| Yi-Coder-9B-Chat-Q5_K_M.gguf | Q5_K_M | 6.26GB | False | High quality, recommended. |
| Yi-Coder-9B-Chat-Q5_K_S.gguf | Q5_K_S | 6.11GB | False | High quality, recommended. |
| Yi-Coder-9B-Chat-Q4_K_L.gguf | Q4_K_L | 5.52GB | False | Uses Q8_0 for embed and output weights. Good quality, recommended. |
| Yi-Coder-9B-Chat-Q4_K_M.gguf | Q4_K_M | 5.33GB | False | Good quality, default size for most use cases, recommended. |
| Yi-Coder-9B-Chat-Q4_K_S.gguf | Q4_K_S | 5.07GB | False | Slightly lower quality with more space savings, recommended. |
| Yi-Coder-9B-Chat-Q4_0.gguf | Q4_0 | 5.05GB | False | Legacy format, generally not worth using over similarly sized formats |
| Yi-Coder-9B-Chat-Q4_0_8_8.gguf | Q4_0_8_8 | 5.04GB | False | Optimized for ARM inference. Requires 'sve' support (see link below). |
| Yi-Coder-9B-Chat-Q4_0_4_8.gguf | Q4_0_4_8 | 5.04GB | False | Optimized for ARM inference. Requires 'i8mm' support (see link below). |
| Yi-Coder-9B-Chat-Q4_0_4_4.gguf | Q4_0_4_4 | 5.04GB | False | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. |
| Yi-Coder-9B-Chat-Q3_K_XL.gguf | Q3_K_XL | 4.92GB | False | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| Yi-Coder-9B-Chat-IQ4_XS.gguf | IQ4_XS | 4.79GB | False | Decent quality, smaller than Q4_K_S with similar performance, recommended. |
| Yi-Coder-9B-Chat-Q3_K_L.gguf | Q3_K_L | 4.69GB | False | Lower quality but usable, good for low RAM availability. |
| Yi-Coder-9B-Chat-Q3_K_M.gguf | Q3_K_M | 4.32GB | False | Low quality. |
| Yi-Coder-9B-Chat-IQ3_M.gguf | IQ3_M | 4.06GB | False | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| Yi-Coder-9B-Chat-Q3_K_S.gguf | Q3_K_S | 3.90GB | False | Low quality, not recommended. |
| Yi-Coder-9B-Chat-IQ3_XS.gguf | IQ3_XS | 3.72GB | False | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| Yi-Coder-9B-Chat-Q2_K_L.gguf | Q2_K_L | 3.61GB | False | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| Yi-Coder-9B-Chat-Q2_K.gguf | Q2_K | 3.35GB | False | Very low quality but surprisingly usable. |
| Yi-Coder-9B-Chat-IQ2_M.gguf | IQ2_M | 3.10GB | False | Relatively low quality, uses SOTA techniques to be surprisingly usable. |