ibm-granite/granite-4.0-1b
Full fine-tune vs ibm-granite/granite-4.0-1b-base. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 66/81, Attention 160/160, MLP 80/80
9 derivatives checked
- ibm-granite/granite-4.0-1b-GGUF: Same weights, converted
- unsloth/granite-4.0-1b-GGUF: Same weights, converted
- DevQuasar/ibm-granite.granite-4.0-1b-GGUF: Same weights, converted
- unsloth/granite-4.0-1b: Identical copy
- OVRLab/granite-4.0-1b-kvshare-experiment: Identical copy
- unsloth/granite-4.0-1b-unsloth-bnb-4bit: Quantization
- WithinUsAI/IBM-Grok4-Ultra.Fast.Coder-1B: Full fine-tune
- 11-47/IBM-GPT5.4-Coder-1B: Full fine-tune
- Oxy29/IBM-GPT5.4-Coder-1B: Full fine-tune
6 other repos hold byte-for-byte identical weight files.