bartowski/Hercules-5.0-Qwen2-1.5B-GGUF-torrent
bartowski/Hercules-5.0-Qwen2-1.5B-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 | Description |
|---|---|---|---|
| Hercules-5.0-Qwen2-1.5B-Q8_0.gguf | Q8_0 | 1646.57MB | Extremely high quality, generally unneeded but max available quant. |
| Hercules-5.0-Qwen2-1.5B-Q6_K.gguf | Q6_K | 1272.73MB | Very high quality, near perfect, recommended. |
| Hercules-5.0-Qwen2-1.5B-Q5_K_M.gguf | Q5_K_M | 1125.04MB | High quality, recommended. |
| Hercules-5.0-Qwen2-1.5B-Q5_K_S.gguf | Q5_K_S | 1098.72MB | High quality, recommended. |
| Hercules-5.0-Qwen2-1.5B-Q4_K_M.gguf | Q4_K_M | 986.04MB | Good quality, uses about 4.83 bits per weight, recommended. |
| Hercules-5.0-Qwen2-1.5B-Q4_K_S.gguf | Q4_K_S | 940.30MB | Slightly lower quality with more space savings, recommended. |
| Hercules-5.0-Qwen2-1.5B-IQ4_XS.gguf | IQ4_XS | 895.72MB | Decent quality, smaller than Q4_K_S with similar performance, recommended. |
| Hercules-5.0-Qwen2-1.5B-Q3_K_L.gguf | Q3_K_L | 880.16MB | Lower quality but usable, good for low RAM availability. |
| Hercules-5.0-Qwen2-1.5B-IQ3_M.gguf | IQ3_M | 776.66MB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |