Hcompany/Holo-3.1-35B-A3B
Different architecture vs Qwen/Qwen3.5-0.8B. Different architecture: only 30 of 488/1026 tensors match by name and shape.
5 derivatives checked
- gbuzhf/Holo-3.1-35B-A3B-MTP-GGUF: Full fine-tune
- mradermacher/Holo-3.1-35B-A3B-i1-GGUF: Quantization
- mradermacher/Holo-3.1-35B-A3B-GGUF: Quantization
- barozp/Holo-3.1-35B-A3B-GGUF: Quantization
- pipenetwork/Holo-3.1-35B-A3B-MLX-4bit: Quantization