empero-ai/Qwythos-9B-v2
Partial fine-tune vs empero-ai/Qwythos-9B-Claude-Mythos-5-1M. Partial change: 84% of the weights changed (attention, lm_head, mlp), in 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 0/4, Norms 0/215, Attention 152/332, MLP 96/208
26 derivatives checked
- empero-ai/Qwythos-9B-v2-GGUF: Same weights, converted
- mradermacher/Qwythos-9B-v2-i1-GGUF: Quantization
- bartowski/empero-ai_Qwythos-9B-v2-GGUF: Same weights, converted
- KikoCis/Qwythos-9B-v2-Full-Ladder-KLD-GGUF: Quantization
- mradermacher/Qwythos-9B-v2-GGUF: Same weights, converted
- mlx-community/Qwythos-9B-v2-OptiQ-4bit: Quantization
- Dzluck/Qwythos-9B-v2-GGUF: Same weights, converted
- Netuoso/qwepus: LoRA-style (fewer layers)
- CobrIX/CobrIX-1.0-Coder-Full-72B-A18B-GGUF: Not comparable yet
- CobrIX/CobrIX-1.0-Coder-Flash-33B-A13B-GGUF: Not comparable yet
- CobrIX/CobrIX-1.5-preview-Coder-Flash-33B-A13B: Different architecture
- sahilchachra/Qwythos-9B-v2-AWQ: Quantization
- Fastiraz/Qwythos-9B-v2-GGUF: Same weights, converted
- brainworkup/Qwythos-9B-v2-MLX-oQ8-mtp: Quantization
- yugeshkarunamurthy/Qwythos-9B-v2-oQe6-MTP: Quantization
- CobrIX/CobrIX-1.0-Coder-Full-72B-A18B: Different architecture
- luxuansang/Qwythos-9B-v2-GGUF: Same weights, converted
- IKN03/Qwythos-9B-v2-GGUF: Same weights, converted
- usermma/Qwythos-9B-v2-Heretic-Abliterated: Partial fine-tune (fewer layers)
- CobrIX/CobrIX-1.5-preview-Coder-Full-72B-A18B: Different architecture
- protoLabsAI/Qwythos-9B-v2-NVFP4: Quantization
- DarkKitsune/Qwythos-9B-v2-Q5_K_L-imat-GGUF: Quantization
- CobrIX/CobrIX-1.0-Coder-Flash-33B-A13B: Different architecture
- yethdev/qwythos-9b-v2-manumit-v2: LoRA-style
- WaveCut/Qwythos-9B-v2-Heretic: Abliterated
- yethdev/qwythos-9b-v2-manumit-v1: LoRA-style
3 other repos hold byte-for-byte identical weight files.