Accio-Lab/occamy-1.0
Partial fine-tune (fewer layers) vs Qwen/Qwen3.6-35B-A3B. Qwen/Qwen3.6-35B-A3B matches part of Accio-Lab/occamy-1.0 (946 of its 31666 tensors; the rest of Accio-Lab/occamy-1.0 has no counterpart). On the shared part: Partial change: 85% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 40 of 40 layers.
Tensors changed: Embeddings 1/4, Attention 243/388, MLP 200/312, Norms 98/241, lm_head 1/1
26 derivatives checked
- Accio-Lab/occamy-1.0-GGUF: Quantization
- SC117/occamy-1.0-abliterated-FIT-GGUF: Not comparable yet
- IsValorum/Occamy-1.0-APEX-I-MiniPlus-V2.1-Abliterated-GGUF: Quantization
- IsValorum/Occamy-1.0-APEX-I-MiniPlus-V2-GGUF: Quantization
- bartowski/Accio-Lab_occamy-1.0-GGUF: Same weights, converted
- IsValorum/Occamy-1.0-APEX-I-MiniPlus-V2.1-GGUF: Quantization
- mradermacher/occamy-1.0-i1-GGUF: Quantization
- Accio-Lab/occamy-1.0-NVFP4: Quantization
- mradermacher/occamy-1.0-GGUF: Quantization
- IsValorum/Occamy-1.0-APEX-I-NanoPlus-GGUF: Full fine-tune
- Accio-Lab/occamy-1.0-APEX-GGUF: Quantization
- AMAImedia/Qwen3.6-35B-A3B-occamy-1.0-BF16-GGUF-MTP: Identical copy
- gbuzhf/Occamy-1.0-Abliterated-Sangreal-ICE: Quantization
- moontato/occamy-1.0-mtp-gguf: Not comparable yet
- fetchingcat/occamy-1.0-mtp-gguf: Different architecture
- Accio-Lab/occamy-1.0-MLX-4bit: Quantization
- Accio-Lab/occamy-1.0-MLX-3bit: Quantization
- NovaeonStudio/Occamy-1.0-oQ8-fp16-mtp: Quantization
- fetchingcat/occamy-ornith-35b-a3b-mtp-gguf: Not comparable yet
- leonsarmiento/Occamy-1.0-6bit-XL-mlx: Quantization
- Accio-Lab/occamy-1.0-FP8: Quantization
- Accio-Lab/occamy-1.0-MLX-6bit: Quantization
- Accio-Lab/occamy-1.0-MLX-nvfp4: Quantization
- Accio-Lab/occamy-1.0-MLX-mxfp4: Quantization
- Accio-Lab/occamy-1.0-MLX-5bit: Quantization
- funnygeeker/occamy-1.0-oQ6e-fp16: Quantization