mistralai/Voxtral-Mini-4B-Realtime-2602
Full fine-tune vs mistralai/Ministral-3-3B-Base-2512. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Embeddings 1/1, Norms 53/53, MLP 78/78, Attention 104/104, other 1/1
15 derivatives checked
- handy-computer/Voxtral-Mini-4B-Realtime-2602-gguf: Not comparable yet
- cstr/voxtral-mini-4b-realtime-GGUF: Not comparable yet
- mlx-community/Voxtral-Mini-4B-Realtime-2602-4bit: Quantization
- andrijdavid/Voxtral-Mini-4B-Realtime-2602-GGUF: Not comparable yet
- mlx-community/Voxtral-Mini-4B-Realtime-2602-fp16: Different architecture
- T0mSIlver/Voxtral-Mini-4B-Realtime-2602-4bit-qhead: Quantization
- x-square-robot/X2-Turn-4B-0812: Full fine-tune
- mlx-community/Voxtral-Mini-4B-Realtime-6bit: Quantization
- ldov/Voxtral-Mini-4B-Realtime-2602-gguf: Not comparable yet
- ghecko78/Voxtral-Mini-4B-Realtime-2602-FP8-Dynamic: Quantization
- TrevorJS/voxtral-mini-realtime-gguf: Different architecture
- openresearchtools/Voxtral-Mini-4B-Realtime-2602: Not comparable yet
- mistralai/Voxtral-Mini-4B-Realtime-Arabic: Full fine-tune
- epapanita/Voxtral-Mini-4B-Realtime-2602-gguf: Not comparable yet
- adriabama06/Voxtral-Mini-4B-Realtime-2602-CrispASR-GGUF: Not comparable yet