TEKIBO/Qwen3.8-1.0B-A0.6B-Q4_0-GGUF

Quantization vs inference-optimization/Qwen3.8-1.0B-A0.6B. TEKIBO/Qwen3.8-1.0B-A0.6B-Q4_0-GGUF is a GGUF quantization (Q4_0) of the same weights: 29 tensors match exactly and 34 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/21, MLP 0/32, Attention 0/8

On the Hub · Downloads on Model Pulse