Quantized Model List

Quantized Model List#

Category Model INT8 Address
DeepSeek DeepSeek-V3.2-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/DeepSeek-V3.2-W8A8-INT8-Dynamic.tar
DeepSeek-V3.2-W8A8-INT8-Dynamic-NextN https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/DeepSeek-V3.2-W8A8-INT8-Dynamic-NextN.tar
DeepSeek-V3.2-Exp-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/DeepSeek-V3.2-Exp-W8A8-INT8-Dynamic.tar
DeepSeek-V3.2-Exp-W8A8-INT8-Dynamic-NextN https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/DeepSeek-V3.2-Exp-W8A8-INT8-Dynamic-NextN.tar
DeepSeek-v3.1-Terminus-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/DeepSeek-V3.1-Terminus-W8A8-INT8-Dynamic.tar
DeepSeek-V3.1-Terminus-W8A8-INT8-Dynamic-NextN https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/DeepSeek-V3.1-Terminus-W8A8-INT8-Dynamic-NextN.tar
Qwen Qwen3.5-397B-A17B-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/Qwen3.5-397B-A17B-W8A8-INT8-Dynamic.tar
Qwen3.5-122B-A10B-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/Qwen3.5-122B-A10B-W8A8-INT8-Dynamic.tar
Qwen3-Next-80B-A3B-Thinking-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/Qwen3-Next-80B-A3B-Thinking-W8A8-INT8-Dynamic.tar
Qwen3-VL-235B-A22B-Thinking-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/Qwen3-VL-235B-A22B-Thinking-W8A8-INT8-Dynamic.tar
Qwen3-VL-235B-A22B-Instruct-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/Qwen3-VL-235B-A22B-Instruct-W8A8-INT8-Dynamic.tar
Qwen3-235B-A22B-Instruct-2507-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/Qwen3-235B-A22B-Instruct-2507-W8A8-INT8-Dynamic.tar
Qwen3-VL-32B-Instruct-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/Qwen3-VL-32B-Instruct-W8A8-INT8-Dynamic.tar
Qwen3-VL-32B-Thinking-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/Qwen3-VL-32B-Thinking-W8A8-INT8-Dynamic.tar
Qwen3-VL-30B-A3B-Instruct-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/Qwen3-VL-30B-A3B-Instruct-W8A8-INT8-Dynamic.tar
Qwen3-VL-30B-A3B-Thinking-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/Qwen3-VL-30B-A3B-Thinking-W8A8-INT8-Dynamic.tar
Qwen3-30B-A3B-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/Qwen3-30B-A3B-W8A8-INT8-Dynamic.tar
Qwen3-4B-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/Qwen3-4B-W8A8-INT8-Dynamic.tar
Qwen2.5-VL-72B-Instruct-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/Qwen2.5-VL-72B-Instruct-W8A8-INT8-Dynamic.tar
GLM GLM-5-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/GLM-5-W8A8-INT8-Dynamic.tar
GLM-4.7-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/GLM-4.7-W8A8-INT8-Dynamic.tar
GLM-4.6-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/GLM-4.6-W8A8-INT8-Dynamic.tar
MiMo MiMo-V2-Flash-BF16 https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/MiMo-V2-Flash-BF16.tar
MiMo-V2-Flash-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/MiMo-V2-Flash-W8A8-INT8-Dynamic.tar
MinMax MiniMax-M2.1-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/MiniMax-M2.1-W8A8-INT8-Dynamic.tar
MiniMax-M2.5-W8A8-INT8-Dynamic https://aihc-private-hcd.bj.bcebos.com/LLM/AICapX-Quant-Models/release_packages/MiniMax-M2.5-W8A8-INT8-Dynamic.tar