zzwkk/MUA-RL-8B
Different architecture vs Qwen/Qwen3-32B. Different architecture: only 72 of 707/399 tensors match by name and shape.
2 derivatives checked
- mradermacher/MUA-RL-8B-i1-GGUF: Quantization
- mradermacher/MUA-RL-8B-GGUF: Same weights, converted