mradermacher/BiPS-Qwen3-i1-GGUF

Quantization (fewer layers) vs zss01/BiPS-Qwen3. mradermacher/BiPS-Qwen3-i1-GGUF matches part of zss01/BiPS-Qwen3 (399 of its 750 tensors; the rest of zss01/BiPS-Qwen3 has no counterpart). On the shared part: mradermacher/BiPS-Qwen3-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 145 tensors match exactly and 254 within quantization error.

Tensors changed: lm_head 0/1, MLP 0/108, Norms 0/145, Attention 0/144, Embeddings 0/1

On the Hub · Downloads on Model Pulse