Tesslate/OmniCoder-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
15 derivatives checked
- Tesslate/OmniCoder-9B-GGUF: Same weights, converted
- bartowski/Tesslate_OmniCoder-9B-GGUF: Same weights, converted
- mradermacher/OmniCoder-9B-i1-GGUF: Quantization
- mradermacher/OmniCoder-9B-GGUF: Same weights, converted
- Kukedlc/Slopus-9B: Full fine-tune
- cyankiwi/OmniCoder-9B-AWQ-4bit: Quantization
- arthurcollet/OmniCoder-9B-mlx-mxfp8: Quantization
- nassimjp/ipashtoCoder-9B-GGUF: Same weights, converted
- NexVeridian/OmniCoder-9B-4bit: Quantization
- iffrce/OmniCoder-9B-GGUF: Same weights, converted
- lainlives/QCoder: Same weights, converted
- armand0e/OmniCoder-9B-Claude-Opus-High-Reasoning-Distill: LoRA-style
- aifeifei798/OmniCoder-Queen-9B: Same weights, repacked
- Tivaphraen/Geryon-9B-v1: Partial fine-tune (fewer layers)
- CosmossG/COSMOS-9B-V1: Abliterated
27 other repos hold byte-for-byte identical weight files.