AI Model Hub

Browse all available AI models with support for multiple inference frameworks

Model Replacement Deployment Guide
Total Models 132
Filtered 132
Available 132
Showing 25-48 / 132 models
Page 2 / 6
Alibaba
Gte_1.5b_2k_b1_2core_1chip
1.5 gguf w4a8 M50 2,048 6 71
Text Vector
HLIECpp HLIEPython HLIELLama

Type: Gte | Size: 1.5 | Quant: w4a8 | Context: 2048 | Chip: M50 | Build: 1.4.0 | Status: Stable

MINICPM
MiniCPM_1.3B_256k_b1_2core_1chip(dynamic)
1.3 gguf w8a8 M50 262,144 Vision 14 95
Text Text

Type: MiniCPM | Size: 1.3 | Quant: w8a8 | Context: 262144 | Chip: M50 | Build: 1.5.0 | Status: Stable

MINICPM
MiniCPM_1.3B_256k_b1_2core_1chip(dynamic)
1.3 gguf w8a8 M50 262,144 Vision 14 95
Text Text
HLIELLama HLIEvLLM

Type: MiniCPM | Size: 1.3 | Quant: w8a8 | Context: 262144 | Chip: M50 | Build: 1.5.0 | Status: Testing

MINICPM-V-4.7
MiniCPM-V-4.7_35b-a3b-dspark_128k_b1_2core_1chip(dynamic_16x)
35 gguf w4a8 M50 131,072 Vision 1
Text Text

Type: MiniCPM-V-4.7 | Size: 35 | Quant: w4a8 | Context: 131072 | Chip: M50 | Build: 1.6.0 | Status: Temporary

MINICPM-V-4.7
MiniCPM-V-4.7_35b-a3b-dspark_128k_b1_2core_1chip(dynamic_16x)
35 gguf w4a8 M50 131,072 Vision 1
Text Text

Type: MiniCPM-V-4.7 | Size: 35 | Quant: w4a8 | Context: 131072 | Chip: M50 | Build: 1.6.0 | Status: Temporary

MINICPM-V-4.7
MiniCPM-V-4.7_35b-a3b-dspark_128k_b1_2core_1chip(dynamic_4x)
35 gguf w4a8 M50 131,072 Vision
Text Text

Type: MiniCPM-V-4.7 | Size: 35 | Quant: w4a8 | Context: 131072 | Chip: M50 | Build: 1.6.0 | Status: Temporary

MINICPM-V-4.7
MiniCPM-V-4.7_35b-a3b-dspark_128k_b1_2core_1chip(dynamic_4x)
35 gguf w4a8 M50 131,072 Vision
Text Text

Type: MiniCPM-V-4.7 | Size: 35 | Quant: w4a8 | Context: 131072 | Chip: M50 | Build: 1.6.0 | Status: Temporary

MINICPM-V-4.7
MiniCPM-V-4.7_35b-a3b_256k_b1_2core_1chip(16x)
35 gguf w4a8 M50 262,144 Vision
Text Text

Type: MiniCPM-V-4.7 | Size: 35 | Quant: w4a8 | Context: 262144 | Chip: M50 | Build: 1.6.0 | Status: Temporary

MINICPM-V-4.7
MiniCPM-V-4.7_35b-a3b_256k_b1_2core_1chip(16x)
35 gguf w4a8 M50 262,144 Vision
Text Text

Type: MiniCPM-V-4.7 | Size: 35 | Quant: w4a8 | Context: 262144 | Chip: M50 | Build: 1.6.0 | Status: Temporary

MINICPM-V-4.7
MiniCPM-V-4.7_35b-a3b_256k_b1_2core_1chip(4x)
35 gguf w4a8 M50 262,144 Vision 2
Text Text

Type: MiniCPM-V-4.7 | Size: 35 | Quant: w4a8 | Context: 262144 | Chip: M50 | Build: 1.6.0 | Status: Temporary

MINICPM-V-4.7
MiniCPM-V-4.7_35b-a3b_256k_b1_2core_1chip(4x)
35 gguf w4a8 M50 262,144 Vision 2
Text Text

Type: MiniCPM-V-4.7 | Size: 35 | Quant: w4a8 | Context: 262144 | Chip: M50 | Build: 1.6.0 | Status: Temporary

MINIMAX-H3
MiniMax-H3_33b__b1_2core_1chip
33 gguf w8a8 M50 5
Text Text
HLIEPython

Type: MiniMax-H3 | Size: 33 | Quant: w8a8 | Chip: M50 | Status: Testing

PADDLEOCR-VL
PaddleOCR-VL_0.9b_16k_b1_2core_1chip(896*896)
0.9 gguf w8a8 M50 16,384 Vision 3
Text, Image Text

Type: PaddleOCR-VL | Size: 0.9 | Quant: w8a8 | Context: 16384 | Chip: M50 | Build: 1.5.0 | Status: Testing

PADDLEOCR-VL
PaddleOCR-VL_0.9b_4k_b1_2core_1chip(896*896)
0.9 gguf w8a8 M50 4,096 Vision
Text, Image Text

Type: PaddleOCR-VL | Size: 0.9 | Quant: w8a8 | Context: 4096 | Chip: M50 | Build: 1.5.0 | Status: Testing

QWEN-AGENTWORLD
Qwen-AgentWorld_35b-a3b_256k_b1_2core_1chip
35 gguf w4a8 M50 262,144 5 72
Text Text
HLIECpp HLIEPython HLIELLama

Type: Qwen-AgentWorld | Size: 35 | Quant: w4a8 | Context: 262144 | Chip: M50 | Build: 1.4.0 | Status: Stable

QWEN-AGENTWORLD
Qwen-AgentWorld_35b-a3b_32k_b1_2core_1chip
35 gguf w4a8 M50 32,768 6 63
Text Text
HLIECpp HLIEPython HLIELLama

Type: Qwen-AgentWorld | Size: 35 | Quant: w4a8 | Context: 32768 | Chip: M50 | Status: Temporary

阿里云
Qwen3_30b-a3b_16k_b4_2core_1chip
30 gguf w4a8 M50 16,384 8 66
Text Text
HLIECpp HLIEPython HLIELLama

Type: Qwen3 | Size: 30 | Quant: w4a8 | Context: 16384 | Chip: M50 | Build: 1.4.0 | Status: Stable

阿里云
Qwen3_30b-a3b_32k_b1_2core_1chip
30 gguf w4a8 M50 32,768 2 35
Text Text
HLIECpp HLIEPython HLIELLama

Type: Qwen3 | Size: 30 | Quant: w4a8 | Context: 32768 | Chip: M50 | Build: 1.3.0 | Status: Stable

阿里云
Qwen3-ASR_0.6b_2k_b1_2core_1chip()
0.6 gguf w4a8 M50 2,048 Vision 7 63
Audio Text
HLIECpp HLIEPython HLIELLama

Type: Qwen3-ASR | Size: 0.6 | Quant: w4a8 | Context: 2048 | Chip: M50 | Build: 1.4.0 | Status: Stable

阿里云
Qwen3-ASR_0.6b__b1_2core_1chip()
0.6 gguf w4a8 M50 Vision 8 67
Audio Text
HLIECpp HLIEPython HLIELLama

Type: Qwen3-ASR | Size: 0.6 | Quant: w4a8 | Chip: M50 | Build: 1.3.0 | Status: Stable

阿里云
Qwen3-ASR_1.7b_2k_b1_2core_1chip()
1.7 gguf w4a8 M50 2,048 Vision 4 45
Audio Text
HLIECpp HLIEPython HLIELLama

Type: Qwen3-ASR | Size: 1.7 | Quant: w4a8 | Context: 2048 | Chip: M50 | Build: 1.4.0 | Status: Stable

阿里云
Qwen3-ASR_1.7b__b1_2core_1chip()
1.7 gguf w4a8 M50 Vision 4 43
Audio Text
HLIECpp HLIEPython HLIELLama

Type: Qwen3-ASR | Size: 1.7 | Quant: w4a8 | Chip: M50 | Build: 1.3.0 | Status: Stable

阿里云
Qwen3-ASR-ForceAligner_0.6b_2k_b1_2core_1chip()
0.6 gguf w4a8 M50 2,048 Vision 5 52
Audio Text
HLIECpp HLIEPython HLIELLama

Type: Qwen3-ASR-ForceAligner | Size: 0.6 | Quant: w4a8 | Context: 2048 | Chip: M50 | Build: 1.4.0 | Status: Testing

阿里云
Qwen3-ASR-ForceAligner_0.6b__b1_2core_1chip()
0.6 gguf w4a8 M50 Vision 5 46
Audio Text
HLIECpp HLIEPython HLIELLama

Type: Qwen3-ASR-ForceAligner | Size: 0.6 | Quant: w4a8 | Chip: M50 | Build: 1.3.0 | Status: Stable