unsloth/Llama-3.2-1B-Instruct-GGUF

Same weights, converted vs meta-llama/Llama-3.2-1B-Instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64

3 derivatives checked

• meshllm/Llama-3.2-1B-Instruct-Q4_K_M-layers: Quantization (fewer layers)
• leeroy-jankins/leeroy: Quantization
• Alindstroem89/Llama-3.2-1B-Instruct_guardrail: LoRA-style

On the Hub · Downloads on Model Pulse