mlx-community/Qwen2.5-1.5B-Instruct-4bit download history
mlx-community/Qwen2.5-1.5B-Instruct-4bit is a 1.5B-parameter text generation model by mlx-community. In the last 30 days it was downloaded 20,322 times (3,757 in the last 7 days), and 952,296 times in total.
It ranks #5,734 on the Hub by monthly downloads and #1,307 among text generation models.
It has 4 likes.
It is a fine-tune of Qwen/Qwen2.5-1.5B.
12 models build on Qwen2.5-1.5B-Instruct-4bit: 6 quantized, 3 fine-tuned, 3 adapters and 0 merges. Together with the original they were downloaded 20,628 times in the last 30 days. See the Qwen2.5-1.5B-Instruct-4bit galaxy.
Most downloaded derivatives
- suraj10620/stark-1.5b (adapter), 70 downloads in 30 days
- ativin/trading-brain-v1 (finetune), 45 downloads in 30 days
- hebertgo/knowledgebase-intent-llm (quantized), 38 downloads in 30 days
- Alillllm/skymod-qwen-1.5b (quantized), 34 downloads in 30 days
- hherbol/swolbro-qwen2.5-1.5b-4bit (quantized), 24 downloads in 30 days
- shruroy/Qwen2.5-1.5B-voice-inject (quantized), 22 downloads in 30 days
- mugegu455/credit-narrative-slm (quantized), 18 downloads in 30 days
- sergiones/Qwen2.5-1.5B-4bit-equation-chat-ft (finetune), 16 downloads in 30 days
- Movs/C3PO-Qwen2.5-1.5B-4bit (quantized), 14 downloads in 30 days
- jarkas/jilid_Qwen2.5-1.5B-Instruct-4bit_v1 (finetune), 13 downloads in 30 days
- dschen/sovereign-weather-lora (adapter), 12 downloads in 30 days
- misbah-dev/trade-parse-qlora (adapter), 0 downloads in 30 days
Open mlx-community/Qwen2.5-1.5B-Instruct-4bit on Hugging Face