Views
No views yet
cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition, UQFF quantization| Quantization type(s) | Example |
|---|---|
| Q4_0 | ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-Q4_0-0.uqff;Dolphin-Mistral-24B-Venice-Edition-Q4_0-1.uqff;Dolphin-Mistral-24B-Venice-Edition-Q4_0-2.uqff" |
| Q4_1 | ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-Q4_1-0.uqff;Dolphin-Mistral-24B-Venice-Edition-Q4_1-1.uqff;Dolphin-Mistral-24B-Venice-Edition-Q4_1-2.uqff" |
| Q5_0 | ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-Q5_0-0.uqff;Dolphin-Mistral-24B-Venice-Edition-Q5_0-1.uqff;Dolphin-Mistral-24B-Venice-Edition-Q5_0-2.uqff" |
| Q5_1 | ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-Q5_1-0.uqff;Dolphin-Mistral-24B-Venice-Edition-Q5_1-1.uqff;Dolphin-Mistral-24B-Venice-Edition-Q5_1-2.uqff" |
| Q8_0 | ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-Q8_0-0.uqff;Dolphin-Mistral-24B-Venice-Edition-Q8_0-1.uqff;Dolphin-Mistral-24B-Venice-Edition-Q8_0-2.uqff;Dolphin-Mistral-24B-Venice-Edition-Q8_0-3.uqff" |
| Q2K | ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff Dolphin-Mistral-24B-Venice-Edition-q2k.uqff |
| Q3K | ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff Dolphin-Mistral-24B-Venice-Edition-q3k.uqff |
| Q4K | ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-q4k-0.uqff;Dolphin-Mistral-24B-Venice-Edition-q4k-1.uqff;Dolphin-Mistral-24B-Venice-Edition-q4k-2.uqff" |
| Q5K | ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-q5k-0.uqff;Dolphin-Mistral-24B-Venice-Edition-q5k-1.uqff;Dolphin-Mistral-24B-Venice-Edition-q5k-2.uqff" |
| Q6K | ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-q6k-0.uqff;Dolphin-Mistral-24B-Venice-Edition-q6k-1.uqff;Dolphin-Mistral-24B-Venice-Edition-q6k-2.uqff" |
| HQQ4 | ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-HQQ4-0.uqff;Dolphin-Mistral-24B-Venice-Edition-HQQ4-1.uqff;Dolphin-Mistral-24B-Venice-Edition-HQQ4-2.uqff" |
| HQQ8 | ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-HQQ8-0.uqff;Dolphin-Mistral-24B-Venice-Edition-HQQ8-1.uqff;Dolphin-Mistral-24B-Venice-Edition-HQQ8-2.uqff;Dolphin-Mistral-24B-Venice-Edition-HQQ8-3.uqff" |
| FP8 | ./mistralrs-server -i plain -m sonicrules1234/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-UQFF --from-uqff "Dolphin-Mistral-24B-Venice-Edition-FP8-0.uqff;Dolphin-Mistral-24B-Venice-Edition-FP8-1.uqff;Dolphin-Mistral-24B-Venice-Edition-FP8-2.uqff;Dolphin-Mistral-24B-Venice-Edition-FP8-3.uqff" |