baidu/ERNIE-4.5-21B-A3B-Thinking
15 derivatives checked
- unsloth/ERNIE-4.5-21B-A3B-Thinking-GGUF: Same weights, converted
- yujiepan/ernie-4.5-moe-tiny-random: Different architecture
- bartowski/baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF: Same weights, converted
- mradermacher/ERNIE-4.5-21B-A3B-Thinking-i1-GGUF: Quantization
- XythicK/ERNIE-4.5-21B-A3B-Thinking-GGUF: Same weights, converted
- gabriellarson/ERNIE-4.5-21B-A3B-Thinking-GGUF: Same weights, converted
- mradermacher/ERNIE-4.5-21B-A3B-Thinking-GGUF: Quantization
- DevQuasar/baidu.ERNIE-4.5-21B-A3B-Thinking-GGUF: Same weights, converted
- mmnga/ERNIE-4.5-21B-A3B-Thinking-gguf: Quantization
- cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit: Quantization
- DavidAU/ERNIE-4.5-37B-A3B-Thinking-Brainstorm20x: Partial fine-tune (fewer layers)
- DavidAU/ERNIE-21B-A3B-GLM-4.7-Flash-Thinking: LoRA-style
- DavidAU/ERNIE-21B-A3B-Thinking-Gemini-3-Pro-High-Reasoning-V2: LoRA-style
- DavidAU/ERNIE-21B-A3B-Claude-4.5-High-OPUS-Thinking: LoRA-style
- seawolf2357/Darwin-gpt-ernie-20b: Different architecture
2 other repos hold byte-for-byte identical weight files.