mradermacher/Gemma4-E2B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF
Same weights, converted (fewer layers) vs ermiaazarkhalili/Gemma4-E2B-SFT-Claude-Opus-Reasoning-Unsloth. mradermacher/Gemma4-E2B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF matches part of ermiaazarkhalili/Gemma4-E2B-SFT-Claude-Opus-Reasoning-Unsloth (565 of its 2011 tensors; the rest of ermiaazarkhalili/Gemma4-E2B-SFT-Claude-Opus-Reasoning-Unsloth has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), plus 36 new tensors.
Tensors changed: Embeddings 0/2, Norms 0/247, MLP 0/105, other 0/71, Attention 0/140