ibm-granite/granite-3.3-8b-instruct download history
ibm-granite/granite-3.3-8b-instruct is an 8.2B-parameter text generation model by ibm-granite. In the last 30 days it was downloaded 73,672 times (14,846 in the last 7 days), and 1,953,583 times in total.
It ranks #3,151 on the Hub by monthly downloads and #695 among text generation models.
It has 161 likes.
It is a fine-tune of ibm-granite/granite-3.3-8b-base.
72 models build on granite-3.3-8b-instruct: 47 quantized, 17 fine-tuned, 8 adapters and 0 merges. Together with the original they were downloaded 157,951 times in the last 30 days. See the granite-3.3-8b-instruct galaxy.
Most downloaded derivatives
- ibm-granite/granite-speech-3.3-8b (finetune), 28.5K downloads in 30 days
- ibm-ai-platform/micro-g3.3-8b-instruct-1b (finetune), 27.4K downloads in 30 days
- ibm-granite/granite-3.3-8b-instruct-GGUF (quantized), 9.6K downloads in 30 days
- ibm-granite/granite-3.3-8b-instruct-FP8 (quantized), 4.1K downloads in 30 days
- bartowski/ibm-granite_granite-3.3-8b-instruct-GGUF (quantized), 2.5K downloads in 30 days
- unsloth/granite-3.3-8b-instruct-GGUF (quantized), 1.2K downloads in 30 days
- mradermacher/granite-3.3-8b-instruct-i1-GGUF (quantized), 822 downloads in 30 days
- ibm-granite/granite-3.3-8b-math-prm-v2 (finetune), 517 downloads in 30 days
- mradermacher/granite-3.3-8b-instruct-GGUF (quantized), 490 downloads in 30 days
- Raymond-dev-546730/ClinicalThought-AI-8B (adapter), 448 downloads in 30 days
- DevQuasar-12/ibm-granite.granite-3.3-8b-instruct-GGUF (quantized), 427 downloads in 30 days
- mlx-community/granite-3.3-8b-instruct-4bit (quantized), 292 downloads in 30 days