prism-ml/Bonsai-27B-gguf
Full fine-tune vs Qwen/Qwen3.6-27B. prism-ml/Bonsai-27B-gguf is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, MLP 192/192, Attention 64/64, lm_head 1/1, Norms 161/161
3 derivatives checked
- dusterbloom/Bonsai-27B-dSpark-MLX-4bit: Quantization
- tokenbrew/Bonsai-27B-Brew-GGUF: Quantization
- TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired: Same weights, converted