Local AI hardware: Raspberry Pi 4

Hardware profile
Hardware Memory Bandwidth Computing power vLLM
Raspberry Pi 4Raspberry Pi 4 Model B 8 GB 8 GBLPDDR4 RAM 12.8 GB/s not available no
Compatible models Estimated speeds, not benchmark results: calculated from memory bandwidth and model size. Real results can differ significantly because there is no precise formula for deriving LLM generation speed from hardware specifications alone.
Model Size Approx. Q4 memory Estimated generation
Fara 1.5 9BDense 9B 5.4 GB 1 tok/s4-bit quantization
Ornith 1.0 9BDense 9B 5.4 GB 1 tok/s4-bit quantization
Ornith 1.5 9BDense 9B 5.4 GB 1 tok/s4-bit quantization
Qwen 3.5 9BDense 9B 5.4 GB 1 tok/s4-bit quantization
Qwythos 9BDense 9B 5.4 GB 1 tok/s4-bit quantization
Granite 4.1 8BDense 8B 4.8 GB 1 tok/s4-bit quantization
Granite 4.2 8BDense 8B 4.8 GB 1 tok/s4-bit quantization
Qwen 3 8BDense 8B 4.8 GB 1 tok/s4-bit quantization
LFM 2.5 8BMoE 8Bactive 1B 4.8 GB 8 tok/s4-bit quantization
Ling 3.0 TinyMoE 7.9Bactive 1.3B 4.7 GB 6 tok/s4-bit quantization
Fara 1.5 4BDense 4B 2.4 GB 2 tok/s4-bit quantization
Gemma 3 4BDense 4B 2.4 GB 2 tok/s4-bit quantization
Qwen 3 4B Instruct 2507Dense 4B 2.4 GB 2 tok/s4-bit quantization
Qwen 3.5 4BDense 4B 2.4 GB 2 tok/s4-bit quantization
Spark X2.5 4BDense 4B 2.4 GB 2 tok/s4-bit quantization
Granite 4.1 3BDense 3B 1.8 GB 3 tok/s4-bit quantization
Granite 4.2 3BDense 3B 1.8 GB 3 tok/s4-bit quantization
Llama 3.2 3B InstructDense 3B 1.8 GB 3 tok/s4-bit quantization
Ministral 3 3BDense 3B 1.8 GB 3 tok/s4-bit quantization
Nanbeige 4.2 3BDense 3B 1.8 GB 3 tok/s4-bit quantization
LFM 3 1.7BDense 1.7B 1 GB 6 tok/s4-bit quantization