Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
LoRA-style vs Qwen/Qwen3.5-9B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, out_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/5, MLP 96/211, Attention 56/336, other 0/1, Norms 0/221
13 derivatives checked
- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-4bit: Quantization
- Alexzander85/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-NVFP4-MLP-FP8KV: Quantization
- andrevp/Qwen3.5-9B-Distilled-OPUS-Heretic-MLX-VLM-4bit: Quantization
- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-6bit: Quantization
- Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-8bit: Quantization
- AITRADER/Jackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-mxfp8-MLX: Quantization
- Sohailhosseini/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-AWQ-W4A16: Quantization
- AI-Joe-git/Darwin-9B-Opus-GGUF: Full fine-tune
- andrevp/Qwen3.5-9B-Distilled-OPUS-Heretic-MLX-VLM-8bit: Quantization
- bingleai/FableOpus-9B-TIES: Partial fine-tune
- bingleai/FableOpus-9B-Delta: Partial fine-tune
- bingleai/FableOpus-9B-Linear: Partial fine-tune
- the-ai-alchemist/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-nethack: LoRA-style
3 other repos hold byte-for-byte identical weight files.