ibm-granite/granite-4.0-1b-speech
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: Norms 81/81, Attention 160/160
7 derivatives checked
- handy-computer/granite-4.0-1b-speech-gguf: Not comparable yet
- mradermacher/granite-4.0-1b-speech-i1-GGUF: Quantization (fewer layers)
- mradermacher/granite-4.0-1b-speech-GGUF: Same weights, converted (fewer layers)
- loom-ai-org/granite-speech-4.0-1b-loom: Not comparable yet
- ibm-granite/granite-4.0-1b-speech-GGUF: Same weights, converted (fewer layers)
- appautomaton/granite-4.0-1b-speech-int8-mlx: Quantization
- epapanita/granite-4.0-1b-speech-gguf: Not comparable yet
2 other repos hold byte-for-byte identical weight files.