DQN-Labs/mistral-7b-it-0.3-mlx-quantized download history
DQN-Labs/mistral-7b-it-0.3-mlx-quantized is a 7.2B-parameter text generation model by DQN-Labs. In the last 30 days it was downloaded 14 times (7 in the last 7 days), and 450 times in total.
It ranks #570,036 on the Hub by monthly downloads and #197,329 among text generation models.
It has 0 likes.
It is a quantization of mistralai/Mistral-7B-Instruct-v0.3.
2 models build on mistral-7b-it-0.3-mlx-quantized: 2 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 34 times in the last 30 days. See the mistral-7b-it-0.3-mlx-quantized galaxy.
Most downloaded derivatives
- DQN-Labs/dqnGPT-v0.1-7B (quantized), 14 downloads in 30 days
- DQN-Labs/dqnGPT-v0.1-7B-MLX (quantized), 6 downloads in 30 days
Open DQN-Labs/mistral-7b-it-0.3-mlx-quantized on Hugging Face