NVIDIA GeForce GTX 1080 Ti

NVIDIA · 11GBGDDR5X · Can run 59 models

Manufacturer	NVIDIA
VRAM	11 GB
Memory Type	GDDR5X
Architecture	Pascal
CUDA Cores	3,584
Bandwidth	484 GB/s
TDP	250W
MSRP	$699
Released	Mar 10, 2017

AI Notes

The GTX 1080 Ti is one of the most popular budget AI cards on the used market. Its 11GB VRAM handles 7B models well and can run 13B with aggressive quantization (Q4). While it lacks tensor cores, its raw CUDA throughput is still respectable for inference. Available for under $250 used, it's one of the cheapest ways to get 11GB VRAM.

Compatible Models

Model	Parameters	Best Quant	VRAM Used	Fit	Est. Speed
Qwen 3 0.6B	600M	Q4_K_M	2.5 GB	Runs	~194 tok/s
Qwen 3.5 0.8B	800M	Q4_K_M	1.5 GB	Runs	~323 tok/s
Gemma 3 1B	1B	Q8_0	2 GB	Runs	~242 tok/s
Llama 3.2 1B	1B	Q8_0	3 GB	Runs	~161 tok/s
DeepSeek R1 1.5B	1.5B	Q8_0	3 GB	Runs	~161 tok/s
SmolLM2 1.7B	1.7B	Q8_0	2.7 GB	Runs	~179 tok/s
Gemma 2 2B	2B	Q8_0	4 GB	Runs	~121 tok/s
Gemma 3n E2B	2B	Q4_K_M	3.3 GB	Runs	~147 tok/s
Gemma 4 E2B	2B	Q4_K_M	4 GB	Runs	~121 tok/s
Qwen 3.5 2B	2B	Q4_K_M	3 GB	Runs	~161 tok/s
Llama 3.2 3B	3B	Q8_0	5 GB	Runs	~97 tok/s
StarCoder2 3B	3B	Q4_K_M	3.5 GB	Runs	~138 tok/s
Phi-3 Mini 3.8B	3.8B	Q8_0	5.8 GB	Runs	~83 tok/s
Phi-4 Mini 3.8B	3.8B	Q4_K_M	4.5 GB	Runs	~108 tok/s
Gemma 3 4B	4B	Q4_K_M	5 GB	Runs	~97 tok/s
Gemma 3n E4B	4B	Q4_K_M	4.5 GB	Runs	~108 tok/s
Gemma 4 E4B	4B	Q4_K_M	6 GB	Runs	~81 tok/s
Qwen 3 4B	4B	Q4_K_M	4.5 GB	Runs	~108 tok/s
Qwen 3.5 4B	4B	Q4_K_M	4.5 GB	Runs	~108 tok/s
Yi 1.5 6B	6B	Q4_K_M	5 GB	Runs	~97 tok/s
Codestral Mamba 7B	7B	Q4_K_M	6.9 GB	Runs	~70 tok/s
DeepSeek R1 7B	7B	Q8_0	9 GB	Runs	~54 tok/s
Falcon 3 7B	7B	Q4_K_M	6.8 GB	Runs	~71 tok/s
InternLM 2.5 7B	7B	Q4_K_M	5.5 GB	Runs	~88 tok/s
Mistral 7B	7B	Q8_0	9 GB	Runs	~54 tok/s
OpenChat 3.5 7B	7B	Q4_K_M	6.9 GB	Runs	~70 tok/s
Qwen 2.5 7B	7B	Q8_0	9 GB	Runs	~54 tok/s
Qwen 2.5 Coder 7B	7B	Q8_0	9 GB	Runs	~54 tok/s
Qwen 2.5 VL 7B	7B	Q4_K_M	7 GB	Runs	~69 tok/s
StarCoder2 7B	7B	Q4_K_M	5.5 GB	Runs	~88 tok/s
WizardLM 2 7B	7B	Q4_K_M	6.9 GB	Runs	~70 tok/s
Aya Expanse 8B	8B	Q4_K_M	6.5 GB	Runs	~74 tok/s
Cogito 8B	8B	Q4_K_M	7.5 GB	Runs	~65 tok/s
DeepSeek R1 8B	8B	Q4_K_M	7.5 GB	Runs	~65 tok/s
Dolphin 3 8B	8B	Q4_K_M	6 GB	Runs	~81 tok/s
Nemotron 3 Nano 8B	8B	Q4_K_M	7.5 GB	Runs	~65 tok/s
Nous Hermes 2 8B	8B	Q4_K_M	6 GB	Runs	~81 tok/s
Qwen 3 8B	8B	Q4_K_M	7.5 GB	Runs	~65 tok/s
Qwen 3.5 9B	9B	Q4_K_M	7.5 GB	Runs	~65 tok/s
Yi 1.5 9B	9B	Q4_K_M	6.5 GB	Runs	~74 tok/s
Yi Coder 9B	9B	Q4_K_M	8 GB	Runs	~61 tok/s
Falcon 3 10B	10B	Q4_K_M	8.5 GB	Runs	~57 tok/s
Llama 3.2 Vision 11B	11B	Q4_K_M	8.5 GB	Runs	~57 tok/s
Granite 3.3 8B	8B	Q8_0	10 GB	Runs (tight)	~48 tok/s
Llama 3.1 8B	8B	Q8_0	10 GB	Runs (tight)	~48 tok/s
Mistral Nemo 12B	12B	Q4_K_M	9.5 GB	Runs (tight)	~51 tok/s
DeepSeek R1 14B	14B	Q4_K_M	9.9 GB	Runs (tight)	~49 tok/s
Phi-4 14B	14B	Q4_K_M	9.9 GB	Runs (tight)	~49 tok/s
Qwen 2.5 14B	14B	Q4_K_M	9.9 GB	Runs (tight)	~49 tok/s
Gemma 2 9B	9B	Q8_0	11 GB	CPU Offload	~13 tok/s
Gemma 3 12B	12B	Q4_K_M	10.5 GB	CPU Offload	~14 tok/s
Phi-4 Reasoning 14B	14B	Q4_K_M	11 GB	CPU Offload	~13 tok/s
Qwen 2.5 Coder 14B	14B	Q4_K_M	12 GB	CPU Offload	~12 tok/s
Qwen 3 14B	14B	Q4_K_M	12 GB	CPU Offload	~12 tok/s
StarCoder2 15B	15B	Q4_K_M	10.5 GB	CPU Offload	~14 tok/s
InternLM 2.5 20B	20B	Q4_K_M	12 GB	CPU Offload	~12 tok/s
gpt-oss 20B	21B	MXFP4	15 GB	CPU Offload	~10 tok/s
Codestral 22B	22B	Q4_K_M	14.7 GB	CPU Offload	~10 tok/s
Qwen 3.5 35B A3B	35B	Q4_K_M	12 GB	CPU Offload	~12 tok/s

55 model(s) are too large for this hardware.