prism-ml/Ternary-Bonsai-8B-gguf

Same weights, converted vs prism-ml/Ternary-Bonsai-8B-unpacked. Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: MLP 0/108, Norms 0/145, Attention 0/144, lm_head 0/1, Embeddings 0/1

2 derivatives checked

• Minarut/Ternary-Bonsai-8B-GGUF-llamacpp-compatible: Quantization
• ewchampion/Ternary-Bonsai-8B-TQ2_0-GGUF: Quantization

On the Hub · Downloads on Model Pulse