OrionLLM/OxCoder-9B
Same weights, converted vs Qwen/Qwen3.5-9B. Same weights stored in another dtype (BF16/F32 → BF16).
Tensors changed: lm_head 0/1, Embeddings 0/4, MLP 0/208, Attention 0/332, Norms 0/215
16 derivatives checked
- prithivMLmods/OxCoder-9B-GGUF: Same weights, converted
- mradermacher/OxCoder-9B-i1-GGUF: Quantization
- wepiqx/OxCoder-9B-MERNIK-GGUF: Quantization
- mradermacher/OxCoder-9B-GGUF: Same weights, converted
- wepiqx/RINIQ-GGUF: Full fine-tune
- nightmedia/Qwen3.5-9B-Theseus-q8-hi-mlx: Quantization
- Blarfursnarg/OxCoder-9B-mlx: Partial fine-tune (fewer layers)
- prithivMLmods/Orion-9B-Agentic-CodeCore-Merge: Full fine-tune
- OmAr-Kader-DeV/OxCoder-9B-mlx-4Bit: Quantization
- OmAr-Kader-DeV/OxCoder-9B-mlx-8Bit: Quantization
- OmAr-Kader-DeV/OxCoder-9B-mlx-6Bit: Quantization
- kingjones777/OxCoder-9B-MTP-ROCmFP4-GGUF: Quantization
- kingjones777/OxCoder-9B-MTP-ROCmFP4-imatrix-GGUF: Quantization
- nightmedia/Qwen3.5-9B-Theseus-1M-q8-mlx: Quantization
- malvavisc0/OxCoder-9B-gptq-int4: Quantization
- nightmedia/Qwen3.5-9B-Theseus: Full fine-tune
27 other repos hold byte-for-byte identical weight files.