Qwen/Qwen3-32B-AWQ
Text Generation • 33B • Updated • 222k • 152
AI-Agent-Stack-Consumer-Hardware
Набор базовых моделей для разработки автономных ИИ-агентов на доступном железе. Проверено под архитектуру 2x 16GB VRAM (RTX 5060 Ti / Blackwell). Бала
-
-
Qwen/Qwen2.5-Coder-32B-Instruct-AWQ
Text Generation • 33B • Updated • 972k • 50 -
stelterlab/Qwen3-Coder-30B-A3B-Instruct-AWQ
Text Generation • 31B • Updated • 85.2k • 9 -
stelterlab/Nemotron-Cascade-2-30B-A3B-AWQ
Text Generation • 5B • Updated • 125 • 4 -
TheBloke/deepseek-coder-33B-instruct-AWQ
Text Generation • 33B • Updated • 608 • 42 -
bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF
Text Generation • 16B • Updated • 56.7k • 202 -
unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF
Text Generation • 31B • Updated • 486k • 1.22k -
sakamakismile/Qwen3.6-27B-Text-NVFP4-MTP
Text Generation • 17B • Updated • 3.92k • 82 -
NVFP4/Qwen3-Coder-30B-A3B-Instruct-FP4
Text Generation • 16B • Updated • 62.2k • 38 -
selimaktas/Qwen3-Coder-30B-A3B-Instruct-NVFP4
17B • Updated • 7 -
unsloth/Qwen3.6-27B-NVFP4
Image-Text-to-Text • 21B • Updated • 236k • 286 -
nvidia/Qwen3.6-27B-NVFP4
Text Generation • 18B • Updated • 312k • 447 -
QuantTrio/Qwen3-Coder-30B-A3B-Instruct-AWQ
Text Generation • 31B • Updated • 30.2k • 13 -
Qwen/Qwen3-32B-GGUF
Text Generation • 33B • Updated • 123k • 78