Llamacpp Quantizations of Qwen1.5-7B-Chat
Using llama.cpp release b2440 for quantization.
Original model: https://huggingface.co/Qwen/Qwen1.5-7B-Chat
Download a file (not the whole branch) from below:
Filename | Quant type | File Size | Description |
---|---|---|---|
Qwen1.5-7B-Chat-Q8_0.gguf | Q8_0 | 8.21GB | Extremely high quality, generally unneeded but max available quant. |
Qwen1.5-7B-Chat-Q6_K.gguf | Q6_K | 6.34GB | Very high quality, near perfect, recommended. |
Qwen1.5-7B-Chat-Q5_K_M.gguf | Q5_K_M | 5.53GB | High quality, very usable. |
Qwen1.5-7B-Chat-Q5_K_S.gguf | Q5_K_S | 5.39GB | High quality, very usable. |
Qwen1.5-7B-Chat-Q5_0.gguf | Q5_0 | 5.39GB | High quality, older format, generally not recommended. |
Qwen1.5-7B-Chat-Q4_K_M.gguf | Q4_K_M | 4.76GB | Good quality, similar to 4.25 bpw. |
Qwen1.5-7B-Chat-Q4_K_S.gguf | Q4_K_S | 4.54GB | Slightly lower quality with small space savings. |
Qwen1.5-7B-Chat-Q4_0.gguf | Q4_0 | 4.51GB | Decent quality, older format, generally not recommended. |
Qwen1.5-7B-Chat-Q3_K_L.gguf | Q3_K_L | 4.21GB | Lower quality but usable, good for low RAM availability. |
Qwen1.5-7B-Chat-Q3_K_M.gguf | Q3_K_M | 3.91GB | Even lower quality. |
Qwen1.5-7B-Chat-Q3_K_S.gguf | Q3_K_S | 3.56GB | Low quality, not recommended. |
Qwen1.5-7B-Chat-Q2_K.gguf | Q2_K | 3.10GB | Extremely low quality, not recommended. |
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
- Downloads last month
- 477