dphn/Dolphin3.0-Mistral-24B download history
dphn/Dolphin3.0-Mistral-24B is a 23.6B-parameter text generation model by dphn. In the last 30 days it was downloaded 1,442 times (400 in the last 7 days), and 20,005 times in total.
It ranks #27,558 on the Hub by monthly downloads and #7,254 among text generation models.
It has 94 likes.
It is a fine-tune of mistralai/Mistral-Small-24B-Base-2501.
48 models build on Dolphin3.0-Mistral-24B: 38 quantized, 0 fine-tuned, 0 adapters and 10 merges. Together with the original they were downloaded 29,799 times in the last 30 days. See the Dolphin3.0-Mistral-24B galaxy.
Most downloaded derivatives
- bartowski/cognitivecomputations_Dolphin3.0-Mistral-24B-GGUF (quantized), 13.1K downloads in 30 days
- eaddario/Dolphin3.0-Mistral-24B-GGUF (quantized), 4.8K downloads in 30 days
- mradermacher/Dolphin3.0-Mistral-24B-i1-GGUF (quantized), 1.5K downloads in 30 days
- mradermacher/Dolphin3.0-Mistral-24B-GGUF (quantized), 1.3K downloads in 30 days
- AIOpsInSpace/Dolphin3.0-R1-Mistral-24B-Patched (quantized), 990 downloads in 30 days
- DevQuasar-7/cognitivecomputations.Dolphin3.0-Mistral-24B-GGUF (quantized), 469 downloads in 30 days
- Valdemardi/Dolphin3.0-Mistral-24B-AWQ (quantized), 359 downloads in 30 days
- weehal/Dolphin3.0-Mistral-24B-mlx-4Bit (quantized), 261 downloads in 30 days
- Saxanth/Heretic-Doliphin3-24b-Base-GGUF (quantized), 204 downloads in 30 days
- tensorblock/Dolphin3.0-Mistral-24B-GGUF (quantized), 140 downloads in 30 days
- moot20/Dolphin3.0-Mistral-24B-MLX-8bits (quantized), 114 downloads in 30 days
- jacobcarajo/Dolphin3.0-Mistral-24B-Q5_K_M-GGUF (quantized), 97 downloads in 30 days