nightmedia/Qwen3.5-9B-OmniCoder-Claude-Polaris

Full fine-tune vs DavidAU/Qwen3.5-9B-Claude-4.6-OS-HERETIC-UNCENSORED-INSTRUCT. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 4/4, Norms 214/215, Attention 330/332, MLP 208/208

3 derivatives checked

• mradermacher/Qwen3.5-9B-OmniCoder-Claude-Polaris-i1-GGUF: Quantization
• mradermacher/Qwen3.5-9B-OmniCoder-Claude-Polaris-GGUF: Same weights, converted
• piotreknow02/Qwen3.5-9B-OmniCoder-Claude-Polaris-mlx-4bit: Quantization

On the Hub · Downloads on Model Pulse