Hardware profile
Hardware	Memory	Bandwidth	Computing power	vLLM
RTX 5060 Ti 16GBCurrent low-cost NVIDIA 16 GB VRAM desktop GPU class	16 GBGPU VRAM	448 GB/s	~759 TOPS	yes

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
GPT-OSS 20BMoE	20.9Bactive 3.6B	12.5 GB	77 tok/s4-bit quantization
Instella-MoE 16B ThinkMoE	16Bactive 2.8B	9.6 GB	95 tok/s4-bit quantization
Qwen 3 14BDense	14B	8.4 GB	28 tok/s4-bit quantization
Gemma 3 12BDense	12B	7.2 GB	33 tok/s4-bit quantization
Gemma 4 12BDense	12B	7.2 GB	33 tok/s4-bit quantization
Fara 1.5 9BDense	9B	5.4 GB	44 tok/s4-bit quantization
Ornith 1.0 9BDense	9B	5.4 GB	44 tok/s4-bit quantization
Ornith 1.5 9BDense	9B	5.4 GB	44 tok/s4-bit quantization
Qwen 3.5 9BDense	9B	5.4 GB	44 tok/s4-bit quantization
Qwythos 9BDense	9B	5.4 GB	44 tok/s4-bit quantization
Granite 4.1 8BDense	8B	4.8 GB	49 tok/s4-bit quantization
Granite 4.2 8BDense	8B	4.8 GB	49 tok/s4-bit quantization
Qwen 3 8BDense	8B	4.8 GB	49 tok/s4-bit quantization
Ling 3.0 TinyMoE	7.9Bactive 1.3B	4.7 GB	177 tok/s4-bit quantization
Fara 1.5 4BDense	4B	2.4 GB	95 tok/s4-bit quantization
Gemma 3 4BDense	4B	2.4 GB	95 tok/s4-bit quantization
Qwen 3 4B Instruct 2507Dense	4B	2.4 GB	95 tok/s4-bit quantization
Qwen 3.5 4BDense	4B	2.4 GB	95 tok/s4-bit quantization
Spark X2.5 4BDense	4B	2.4 GB	95 tok/s4-bit quantization
Granite 4.1 3BDense	3B	1.8 GB	124 tok/s4-bit quantization
Granite 4.2 3BDense	3B	1.8 GB	124 tok/s4-bit quantization
Llama 3.2 3B InstructDense	3B	1.8 GB	124 tok/s4-bit quantization
Ministral 3 3BDense	3B	1.8 GB	124 tok/s4-bit quantization
Nanbeige 4.2 3BDense	3B	1.8 GB	124 tok/s4-bit quantization