Views
No views yet
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant| Filename | Quant type | File Size | Split | Description |
|---|---|---|---|---|
| Qwen2.5-7B-Instruct-1M-F32.gguf | f32 | 30.5 GB | false | Full F32 weights. |
| Qwen2.5-7B-Instruct-1M-F16.gguf | f16 | 15.24 GB | false | Full F16 weights. |
| Qwen2.5-7B-Instruct-1M-Q8_0.gguf | Q8_0 | 8.10 GB | false | Extremely high quality, generally unneeded but max available quant. |
| Qwen2.5-7B-Instruct-1M-Q6_K.gguf | Q6_K | 6.25 GB | false | Very high quality, near perfect, recommended. |
| Qwen2.5-7B-Instruct-1M-Q5_K_M.gguf | Q5_K_M | 5.44 GB | false | High quality, recommended. |
| Qwen2.5-7B-Instruct-1M-Q5_K_S.gguf | Q5_K_S | 5.32 GB | false | High quality, recommended. |
| Qwen2.5-7B-Instruct-1M-Q4_1.gguf | Q4_1 | 4.87 GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| Qwen2.5-7B-Instruct-1M-Q4_K_M.gguf | Q4_K_M | 4.68 GB | false | Good quality, default size for most use cases, recommended. |
| Qwen2.5-7B-Instruct-1M-Q4_K_S.gguf | Q4_K_S | 4.46 GB | false | Slightly lower quality with more space savings, recommended. |
| Qwen2.5-7B-Instruct-1M-Q4_0.gguf | Q4_0 | 4.43 GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| Qwen2.5-7B-Instruct-1M-Q3_K_L.gguf | Q3_K_L | 4.09 GB | false | Lower quality but usable, good for low RAM availability. |
| Qwen2.5-7B-Instruct-1M-Q3_K_M.gguf | Q3_K_M | 3.81 GB | false | Low quality. |
| Qwen2.5-7B-Instruct-1M-Q3_K_S.gguf | Q3_K_S | 3.49 GB | false | Low quality, not recommended. |
| Qwen2.5-7B-Instruct-1M-Q2_K.gguf | Q2_K | 3.02 GB | false | Very low quality but surprisingly usable. |
pip install -U "huggingface_hub[cli]"huggingface-cli download BabaK07/Qwen2.5-7b-Instruct-1M-Q4_K_M-gguf --include "Qwen2.5-7b-Instruct-1M-Q4_K_M.gguf" --local-dir ./