Views
No views yet
chatml1<|im_start|>system
2{system_message}<|im_end|>
3<|im_start|>user
4{prompt}<|im_end|>
5<|im_start|>assistant320001wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-Coder-3B-Instruct-Q5_K_M.gguf \
2 llama-api-server.wasm \
3 --model-name Qwen2.5-Coder-3B-Instruct \
4 --prompt-template chatml \
5 --ctx-size 320001wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-Coder-3B-Instruct-Q5_K_M.gguf \
2 llama-chat.wasm \
3 --prompt-template chatml \
4 --ctx-size 32000| Name | Quant method | Bits | Size | Use case |
|---|---|---|---|---|
| Qwen2.5-Coder-3B-Instruct-Q2_K.gguf | Q2_K | 2 | 1.27 GB | smallest, significant quality loss - not recommended for most purposes |
| Qwen2.5-Coder-3B-Instruct-Q3_K_L.gguf | Q3_K_L | 3 | 1.71 GB | small, substantial quality loss |
| Qwen2.5-Coder-3B-Instruct-Q3_K_M.gguf | Q3_K_M | 3 | 1.59 GB | very small, high quality loss |
| Qwen2.5-Coder-3B-Instruct-Q3_K_S.gguf | Q3_K_S | 3 | 1.45 GB | very small, high quality loss |
| Qwen2.5-Coder-3B-Instruct-Q4_0.gguf | Q4_0 | 4 | 1.82 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf | Q4_K_M | 4 | 1.93 GB | medium, balanced quality - recommended |
| Qwen2.5-Coder-3B-Instruct-Q4_K_S.gguf | Q4_K_S | 4 | 1.83 GB | small, greater quality loss |
| Qwen2.5-Coder-3B-Instruct-Q5_0.gguf | Q5_0 | 5 | 2.17 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Qwen2.5-Coder-3B-Instruct-Q5_K_M.gguf | Q5_K_M | 5 | 2.22 GB | large, very low quality loss - recommended |
| Qwen2.5-Coder-3B-Instruct-Q5_K_S.gguf | Q5_K_S | 5 | 2.17 GB | large, low quality loss - recommended |
| Qwen2.5-Coder-3B-Instruct-Q6_K.gguf | Q6_K | 6 | 2.54 GB | very large, extremely low quality loss |
| Qwen2.5-Coder-3B-Instruct-Q8_0.gguf | Q8_0 | 8 | 3.29 GB | very large, extremely low quality loss - not recommended |
| Qwen2.5-Coder-3B-Instruct-f16.gguf | f16 | 16 | 6.18 GB |