Views
No views yet
exaone-deep-chat1[|system|]{system_message}[|endofturn|]
2[|user|]{user_message_1}
3[|assistant|]{assistant_message_1}[|endofturn|]
4[|user|]{user_message_2}
5[|assistant|]<thought>320001wasmedge --dir .:. --nn-preload default:GGML:AUTO:EXAONE-Deep-7.8B-Q5_K_M.gguf \
2 llama-api-server.wasm \
3 --prompt-template exaone-deep-chat \
4 --ctx-size 32000 \
5 --model-name EXAONE-Deep-7.8B1wasmedge --dir .:. --nn-preload default:GGML:AUTO:EXAONE-Deep-7.8B-Q5_K_M.gguf \
2 llama-chat.wasm \
3 --prompt-template exaone-deep-chat \
4 --ctx-size 32000| Name | Quant method | Bits | Size | Use case |
|---|---|---|---|---|
| EXAONE-Deep-7.8B-Q2_K.gguf | Q2_K | 2 | 3.05 GB | smallest, significant quality loss - not recommended for most purposes |
| EXAONE-Deep-7.8B-Q3_K_L.gguf | Q3_K_L | 3 | 4.19 GB | small, substantial quality loss |
| EXAONE-Deep-7.8B-Q3_K_M.gguf | Q3_K_M | 3 | 3.88 GB | very small, high quality loss |
| EXAONE-Deep-7.8B-Q3_K_S.gguf | Q3_K_S | 3 | 3.53 GB | very small, high quality loss |
| EXAONE-Deep-7.8B-Q4_0.gguf | Q4_0 | 4 | 4.51 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| EXAONE-Deep-7.8B-Q4_K_M.gguf | Q4_K_M | 4 | 4.77 GB | medium, balanced quality - recommended |
| EXAONE-Deep-7.8B-Q4_K_S.gguf | Q4_K_S | 4 | 4.54 GB | small, greater quality loss |
| EXAONE-Deep-7.8B-Q5_0.gguf | Q5_0 | 5 | 5.44 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| EXAONE-Deep-7.8B-Q5_K_M.gguf | Q5_K_M | 5 | 5.57 GB | large, very low quality loss - recommended |
| EXAONE-Deep-7.8B-Q5_K_S.gguf | Q5_K_S | 5 | 5.44 GB | large, low quality loss - recommended |
| EXAONE-Deep-7.8B-Q6_K.gguf | Q6_K | 6 | 6.42 GB | very large, extremely low quality loss |
| EXAONE-Deep-7.8B-Q8_0.gguf | Q8_0 | 8 | 8.31 GB | very large, extremely low quality loss - not recommended |
| EXAONE-Deep-7.8B-f16.gguf | f16 | 16 | 15.6 GB |