microsoft/Phi-4-reasoning
Full fine-tune vs microsoft/phi-4. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 81/81, MLP 80/80, Attention 80/80, lm_head 1/1
13 derivatives checked
- bartowski/microsoft_Phi-4-reasoning-GGUF: Same weights, converted
- microsoft/Phi-4-reasoning-vision-15B: Full fine-tune (fewer layers)
- unsloth/Phi-4-reasoning-GGUF: Same weights, converted
- mradermacher/Phi-4-reasoning-i1-GGUF: Quantization
- lmstudio-community/Phi-4-reasoning-GGUF: Quantization
- mradermacher/Phi-4-reasoning-GGUF: Quantization
- RedHatAI/Phi-4-reasoning-vision-15B: Full fine-tune (fewer layers)
- lmstudio-community/Phi-4-reasoning-MLX-4bit: Quantization
- DevQuasar/microsoft.Phi-4-reasoning-GGUF: Same weights, converted
- unsloth/phi-4-reasoning-unsloth-bnb-4bit: Quantization
- PS4CoT/phi4-reasoning-sdf-false-1k: Abliterated
- ghostoverflow/Phi-4-reasoning-Q4_K_M-GGUF: Quantization
- jkim96/Phi-4-reasoning-DASHQ-Q2-GGUF: Quantization
6 other repos hold byte-for-byte identical weight files.