lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled
LoRA-style vs Qwen/Qwen3.6-35B-A3B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 10 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/5, Attention 40/392, MLP 0/399, Norms 0/247, lm_head 0/1, other 0/1
30 derivatives checked
- huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-MTP-GGUF: Abliterated
- mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-GGUF: Same weights, converted
- mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF: Same weights, converted
- lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-IQ4_XS-GGUF: Quantization
- mradermacher/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-i1-GGUF: Quantization
- RomanOneAndFun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-MTP-APEX_I-Quality_Q6: Quantization
- burningfeet/backup2026-09-20-mudler-Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-GGUF: Same weights, converted
- mradermacher/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-GGUF: Quantization
- huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated: Abliterated
- splats/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ4e: Quantization
- Momix-44/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated: Abliterated
- lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q5_K_M-GGUF: Quantization
- Gustav0-Freind/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-MTP-GGUF: Abliterated
- lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q8_0-GGUF: Quantization
- ddndm/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-GGUF: Same weights, converted
- Sociopacific/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-GPTQ-Int4: Quantization
- Dyluhn/lordx64-Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-MTP-GGUF: Quantization
- Litwein/Qwen3.6-35B-A3B-Claude-4.7-Opus-oQ4e-DWQ-MC-MTP-Vision-MLX: Quantization
- wangkezun/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Text-MLX-oQ6: Quantization
- splats/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ8e: Quantization
- lordx64/Qwable-v1: LoRA-style
- feanors/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-AWQ-INT4: Quantization
- AntimatterAI/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-MLX-5bit: Quantization
- Litwein/Qwen3.6-35B-A3B-Claude-4.7-Opus-oQ4-MTP-MLX: Quantization
- lordx64/Qwable-v2: LoRA-style
- hotdogs/qwen3.6-35b-opus-to-kimi-lora: Adapter
- Litwein/Qwen3.6-35B-A3B-Claude-4.7-Opus-oQ4e-DWQ-MC-MTP-MLX: Quantization
- Litwein/Qwen3.6-35B-A3B-Claude-4.7-Opus-DWQ4-MTP-MLX: Quantization
- splats/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ6e: Quantization
- gopi87/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-Q4_K_M-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.