Quantized models for llm on prem RnD
riccardo preite
rpreite
AI & ML interests
None yet
Recent Activity
updated
a collection
5 days ago
Working Embeddings model
updated
a collection
5 days ago
Working Embeddings model
updated
a collection
5 days ago
Working Generation models
Organizations
None yet
models
23
rpreite/Qwen3_BNB_8bit
15B
•
Updated
•
18
rpreite/Qwen3_GPTQ_SmoothQuant_W8A8
15B
•
Updated
•
15
rpreite/Qwen3_AWQ_W4A16
3B
•
Updated
•
41
rpreite/Gemma3_AWQ_W4A16_no_128
4B
•
Updated
•
17
rpreite/Gemma3_AWQ_W4A16_SMOOTH
14B
•
Updated
•
22
rpreite/Gemma3_AWQ_W4A16
14B
•
Updated
•
4
rpreite/Qwen3_GPTQ_W4A16
3B
•
Updated
•
19
rpreite/Gemma3_GPTQ_W4A16
4B
•
Updated
•
77
rpreite/Apertus-8B-Instruct-2509-BNB-INT4
Text Generation
•
8B
•
Updated
•
82
rpreite/gemma-3-12b-it-BNB-INT4
Image-Text-to-Text
•
Updated
•
161
datasets
0
None public yet