AnkitAI/Parable-Granite-4.1-8B-Claude-Fable-5
LoRA-style vs ibm-granite/granite-4.1-8b. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 120/120, Attention 160/160
5 derivatives checked
- mradermacher/Parable-Granite-4.1-8B-Claude-Fable-5-i1-GGUF: Full fine-tune
- mradermacher/Parable-Granite-4.1-8B-Claude-Fable-5-GGUF: LoRA-style
- nightmedia/granite-4.1-8b-Tangerine: Full fine-tune
- nightmedia/granite-4.1-8b-USS-Nexus-q8-hi-mlx: Quantization
- nightmedia/granite-4.1-8b-Tangerine-q8-hi-mlx: Quantization