DavidAU/Qwen3.5-13B-GLM-4.7-Flash-DeepSeek-Polaris-Grande-Deep-Thinking

Partial fine-tune vs Qwen/Qwen3.5-9B. Partial change: 72% of the weights changed (attention, mlp, norms), in 32 of 32 layers.

Tensors changed: lm_head 0/1, Embeddings 0/5, MLP 96/211, Attention 197/336, Norms 65/221

3 derivatives checked

• mradermacher/Qwen3.5-13B-GLM-4.7-Flash-DeepSeek-Polaris-Grande-Deep-Thinking-i1-GGUF: Quantization
• mradermacher/Qwen3.5-13B-GLM-4.7-Flash-DeepSeek-Polaris-Grande-Deep-Thinking-GGUF: Quantization
• firedancer/Qwen3.5-13B-GLM-4.7-Flash-DeepSeek-Polaris-Grande-Deep-Thinking-GGUF: Quantization

On the Hub · Downloads on Model Pulse