mradermacher/Qwen3-1.6B-A0.9B-i1-GGUF

Quantization vs inference-optimization/Qwen3-1.6B-A0.9B. mradermacher/Qwen3-1.6B-A0.9B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 51 tensors match exactly and 42 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/41, MLP 0/10, Attention 0/40

On the Hub · Downloads on Model Pulse