mradermacher/sphinx-qwen3-8b-i1-GGUF

Quantization (fewer layers) vs maveryn/sphinx-qwen3-8b. mradermacher/sphinx-qwen3-8b-i1-GGUF matches part of maveryn/sphinx-qwen3-8b (399 of its 750 tensors; the rest of maveryn/sphinx-qwen3-8b has no counterpart). On the shared part: mradermacher/sphinx-qwen3-8b-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 145 tensors match exactly and 254 within quantization error.

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

On the Hub · Downloads on Model Pulse