What are the best models to run on NVIDIA RTX 5060 Ti (16GB)?

Based on model rankings and 16 GB usable VRAM: Top Overall: Qwen 3.8 27B (INT4) ~21 tok/s. Top Coding: Qwen3.5-27B (INT4) ~21 tok/s. Optimal Daily Driver: Phi-4 Reasoning Plus (INT4) ~31 tok/s. Maximum Model Size: ERNIE-4.5-VL-28B-A3B (INT4) ~101 tok/s.

How are VRAM, throughput, and latency calculated?

Calculations are determined using apxml.com modeling, combining LLM architecture analysis with GPU hardware physics. VRAM and Context Scaling: Memory requirements are determined from model architecture, including parameter count, layer configuration, and attention structure. The KV cache footprint scales deterministically based on context length, batch size, and cache precision. Throughput (TPS): Token generation is calculated in the memory-bandwidth-bound decode phase, measuring the time required to stream model weights and KV cache relative to hardware memory bandwidth. Latency (TTFT): Time to first token is calculated from the compute operations required during prompt prefill relative to hardware tensor compute capacity.

How accurate are these estimates?

Calculations are calibrated against empirical ground-truth benchmark runs across diverse architectures and hardware. Because the underlying mechanics are benchmark-calibrated, estimates remain accurate across different configurations without needing to run physical tests for every scenario. VRAM Accuracy: Memory estimates are deterministic and closely match actual allocation. Minor differences typically stay within 3% to 5% due to CUDA runtime overhead or memory allocator fragmentation. Speed and Latency Accuracy: Throughput and TTFT typically vary within 5% to 10% depending on the specific inference runtime, kernel implementations, and system power limits.

Best Models to Run on NVIDIA RTX 5060 Ti (16GB) (October 2026)

Rank	Model	Parameters	Precision	TPS (Approx.)	TTFT
#33	Qwen 3.8 27B	27B	INT4	21 tok/s	~3.7s
#83	Qwen3.5-27B	27B	INT4	21 tok/s	~3.7s
#100	Phi-4 Reasoning Plus	14B	INT4	31 tok/s	~1.7s
#101	MiMo V2 Flash	15B (309B active)	INT4	2 tok/s	~37.0s
#108	Gemma 4 26B A4B	25.2B (3.8B active)	INT4	96 tok/s	~611 ms
#109	Gemma 4 12B	11.95B	INT4 Q8	35 tok/s 21 tok/s	~1.4s ~1.7s
#113	Qwen3.5-9B	9B	INT4 Q8	61 tok/s 37 tok/s	~1.1s ~1.1s
#118	K2 Horizon 7B	7B	INT4 Q8 FP16	74 tok/s 46 tok/s 22 tok/s	~836 ms ~844 ms ~1.0s
#128	NVIDIA Nemotron 3 Nano 30B-A3B	3.5B (30B active)	INT4 Q8 FP16	20 tok/s 12 tok/s 6 tok/s	~3.4s ~3.4s ~3.5s
#132	Qwen3.5-4B	4B	INT4 Q8 FP16	111 tok/s 73 tok/s 41 tok/s	~492 ms ~497 ms ~508 ms
#136	GPT-OSS 20B	21B (3.6B active)	INT4	43 tok/s	~630 ms
#146	Granite 4.2 8B	8B	INT4 Q8	67 tok/s 41 tok/s	~950 ms ~960 ms
#150	Gemma 4 E4B	8B	INT4 Q8	67 tok/s 41 tok/s	~950 ms ~960 ms
#158	GLM-4V	9B	INT4 Q8	44 tok/s 29 tok/s	~1.1s ~1.2s
#159	Gemma 3 27B	27B	INT4	21 tok/s	~3.7s
#160	Phi-4	14B	INT4 Q8	42 tok/s 22 tok/s	~1.6s ~1.9s
#169	OLMo 3 7B Think	7B	INT4 Q8	53 tok/s 37 tok/s	~841 ms ~849 ms
#172	DeepSeek-R1 14B	14B	INT4 Q8	43 tok/s 23 tok/s	~1.6s ~1.9s
#173	Ministral 3 14B	14B	INT4	31 tok/s	~1.7s
#177	Gemma 3 12B	12B	INT4 Q8	48 tok/s 27 tok/s	~1.4s ~1.6s
#181	Mistral-Small-2501	24B	INT4	25 tok/s	~3.0s
#182	Ministral 3 8B	8B	INT4 Q8	48 tok/s 34 tok/s	~956 ms ~965 ms
#183	Qwen3.5-2B	2B	INT4 Q8 FP16	166 tok/s 119 tok/s 73 tok/s	~264 ms ~267 ms ~272 ms
#184	MiniCPM5-2B	2B	INT4 Q8 FP16	166 tok/s 119 tok/s 73 tok/s	~264 ms ~267 ms ~272 ms
#185	Qwen2.5-14B	14B	INT4 Q8	42 tok/s 22 tok/s	~1.6s ~1.9s
#186	Gemma 2 27B	27B	INT4	21 tok/s	~3.7s
#188	Gemma 4 E2B	5.1B	INT4 Q8 FP16	94 tok/s 60 tok/s 33 tok/s	~618 ms ~625 ms ~638 ms
#189	Qwen3-4B	4B	INT4 Q8 FP16	111 tok/s 73 tok/s 41 tok/s	~492 ms ~497 ms ~508 ms
#190	DeepSeek-R1 8B	8B	INT4 Q8	69 tok/s 41 tok/s	~950 ms ~960 ms
#193	Ministral 3 3B	3B	INT4 Q8 FP16	89 tok/s 69 tok/s 45 tok/s	~382 ms ~385 ms ~393 ms
#195	Qwen3-14B	14B	INT4 Q8	42 tok/s 22 tok/s	~1.6s ~1.9s
#197	Gemma 2 9B	9B	INT4 Q8	61 tok/s 37 tok/s	~1.1s ~1.1s
#198	Qwen2.5-7B	7B	INT4 Q8 FP16	74 tok/s 46 tok/s 22 tok/s	~836 ms ~844 ms ~1.0s
#199	Qwen3-8B	8B	INT4 Q8	67 tok/s 41 tok/s	~950 ms ~960 ms
#200	Gemma 3 4B	4B	INT4 Q8 FP16	111 tok/s 73 tok/s 41 tok/s	~492 ms ~497 ms ~508 ms
#201	DeepSeek-R1 7B	7B	INT4 Q8 FP16	76 tok/s 47 tok/s 24 tok/s	~836 ms ~844 ms ~935 ms
#202	Llama 3.1 8B	8B	INT4 Q8	67 tok/s 41 tok/s	~950 ms ~960 ms
#204	Qwen3-1.7B	1.7B	INT4 Q8 FP16	180 tok/s 132 tok/s 83 tok/s	~227 ms ~229 ms ~233 ms
#206	Gemma 3 270M	0.27B	INT4 Q8 FP16	288 tok/s 265 tok/s 223 tok/s	~41 ms ~42 ms ~42 ms
#208	Llama 3 8B	8B	INT4 Q8	67 tok/s 41 tok/s	~950 ms ~960 ms
#209	Qwen3-0.6B	0.6B	INT4 Q8 FP16	271 tok/s 227 tok/s 167 tok/s	~84 ms ~85 ms ~86 ms
#210	Phi-4-Mini	3.8B	INT4 Q8 FP16	115 tok/s 76 tok/s 43 tok/s	~470 ms ~474 ms ~484 ms
#212	Ministral-8B-2410	8B	INT4 Q8	67 tok/s 41 tok/s	~950 ms ~960 ms
#213	DeepSeek-R1 1.5B	1.5B	INT4 Q8 FP16	192 tok/s 143 tok/s 92 tok/s	~202 ms ~203 ms ~207 ms
#214	Llama 3.2 3B	3B	INT4 Q8 FP16	133 tok/s 90 tok/s 53 tok/s	~378 ms ~382 ms ~389 ms
#215	Qwen3.5-0.8B	0.8B	INT4 Q8 FP16	247 tok/s 200 tok/s 141 tok/s	~111 ms ~112 ms ~114 ms
#216	Phi-3-mini	3.8B	INT4 Q8 FP16	115 tok/s 76 tok/s 43 tok/s	~470 ms ~474 ms ~484 ms
#217	Gemma 3n E2B IT	6B (2B active)	INT4 Q8 FP16	89 tok/s 76 tok/s 52 tok/s	~287 ms ~289 ms ~318 ms
#218	Mistral-7B-Instruct-v0.1	7.3B	INT4 Q8 FP16	72 tok/s 44 tok/s 22 tok/s	~870 ms ~878 ms ~1.1s
#219	Llama 3.2 1B	1B	INT4 Q8 FP16	227 tok/s 179 tok/s 122 tok/s	~140 ms ~141 ms ~143 ms
#220	Gemma 2 2B	2B	INT4 Q8 FP16	166 tok/s 119 tok/s 73 tok/s	~264 ms ~267 ms ~272 ms
#221	Phi-3-medium	14B	INT4 Q8	42 tok/s 22 tok/s	~1.6s ~1.9s
#222	OLMo 3 7B Instruct	7B	INT4 Q8	53 tok/s 37 tok/s	~841 ms ~849 ms
#224	Qwen2-7B	7B	INT4 Q8 FP16	74 tok/s 46 tok/s 22 tok/s	~836 ms ~844 ms ~1.0s
#225	Phi-3-small	7B	INT4 Q8 FP16	74 tok/s 46 tok/s 22 tok/s	~836 ms ~844 ms ~1.0s
#226	Gemma 3 1B	1B	INT4 Q8 FP16	227 tok/s 179 tok/s 122 tok/s	~140 ms ~141 ms ~143 ms
#227	Mistral-7B-Instruct-v0.2	7.3B	INT4 Q8 FP16	72 tok/s 44 tok/s 22 tok/s	~870 ms ~878 ms ~1.1s
#229	Gemma 1 7B	7B	INT4 Q8	53 tok/s 37 tok/s	~841 ms ~849 ms
#230	Gemma 1 2B	2B	INT4 Q8 FP16	176 tok/s 124 tok/s 75 tok/s	~264 ms ~266 ms ~272 ms
#231	ChatGLM3-6B	6B	INT4 Q8 FP16	59 tok/s 42 tok/s 24 tok/s	~726 ms ~733 ms ~812 ms
#232	ChatGLM2-6B	6B	INT4 Q8 FP16	59 tok/s 42 tok/s 24 tok/s	~726 ms ~733 ms ~812 ms
#233	ChatGLM-6B	6B	INT4 Q8 FP16	59 tok/s 42 tok/s 24 tok/s	~726 ms ~733 ms ~812 ms
Unranked Models (Sorted by Speed)
-	Qwen2-0.5B	0.5B	INT4 Q8 FP16	284 tok/s 243 tok/s 184 tok/s	~71 ms ~71 ms ~73 ms
-	Qwen2.5-0.5B	0.5B	INT4 Q8 FP16	284 tok/s 243 tok/s 184 tok/s	~71 ms ~71 ms ~73 ms
-	ERNIE-4.5-0.3B	0.3B	INT4 Q8 FP16	279 tok/s 256 tok/s 213 tok/s	~45 ms ~46 ms ~47 ms
-	ERNIE-4.5-0.3B-Base	0.3B	INT4 Q8 FP16	279 tok/s 256 tok/s 213 tok/s	~45 ms ~46 ms ~47 ms
-	Falcon-1B	1B	INT4 Q8 FP16	238 tok/s 186 tok/s 125 tok/s	~139 ms ~141 ms ~143 ms
-	Falcon3-1B	1B	INT4 Q8 FP16	227 tok/s 179 tok/s 122 tok/s	~140 ms ~141 ms ~143 ms
-	Qwen2-1.5B	1.5B	INT4 Q8 FP16	192 tok/s 143 tok/s 92 tok/s	~202 ms ~203 ms ~207 ms
-	Qwen2.5-1.5B	1.5B	INT4 Q8 FP16	192 tok/s 143 tok/s 92 tok/s	~202 ms ~203 ms ~207 ms
-	Spark X2.5 1.7B	1.7B	INT4 Q8 FP16	180 tok/s 132 tok/s 83 tok/s	~227 ms ~229 ms ~233 ms
-	Hy-MT2 1.8B	1.8B	INT4 Q8 FP16	175 tok/s 128 tok/s 80 tok/s	~239 ms ~241 ms ~246 ms
-	Falcon-3B	3B	INT4 Q8 FP16	141 tok/s 94 tok/s 54 tok/s	~378 ms ~381 ms ~389 ms
-	CroissantLLM Base	1.3B	INT4 Q8 FP16	138 tok/s 117 tok/s 83 tok/s	~179 ms ~180 ms ~183 ms
-	Phi-1	1.3B	INT4 Q8 FP16	138 tok/s 117 tok/s 83 tok/s	~179 ms ~180 ms ~183 ms
-	Phi-1.5	1.3B	INT4 Q8 FP16	138 tok/s 117 tok/s 83 tok/s	~179 ms ~180 ms ~183 ms
-	DeepSeek-R1 3B	3B	INT4 Q8 FP16	135 tok/s 91 tok/s 53 tok/s	~378 ms ~381 ms ~389 ms
-	Falcon3-3B	3B	INT4 Q8 FP16	133 tok/s 90 tok/s 53 tok/s	~378 ms ~382 ms ~389 ms
-	Qwen2.5-3B	3B	INT4 Q8 FP16	133 tok/s 90 tok/s 53 tok/s	~378 ms ~382 ms ~389 ms
-	ERNIE-4.5-21B-A3B	21B (3B active)	INT4	111 tok/s	~500 ms
-	ERNIE-4.5-21B-A3B-Base	21B (3B active)	INT4	111 tok/s	~500 ms
-	Spark X2.5 4B	4B	INT4 Q8 FP16	111 tok/s 73 tok/s 41 tok/s	~492 ms ~497 ms ~508 ms
-	ERNIE-4.5-VL-28B-A3B	28B (3B active)	INT4	101 tok/s	~568 ms
-	ERNIE-4.5-VL-28B-A3B-Base	28B (3B active)	INT4	101 tok/s	~568 ms
-	Phi-2	2.7B	INT4 Q8 FP16	94 tok/s 74 tok/s 48 tok/s	~347 ms ~350 ms ~357 ms
-	MaLLaM-3B	3B	INT4 Q8 FP16	89 tok/s 69 tok/s 45 tok/s	~382 ms ~385 ms ~393 ms
-	SmolLM3 3B	3B	INT4 Q8 FP16	89 tok/s 69 tok/s 45 tok/s	~382 ms ~385 ms ~393 ms
-	Falcon-7B	7B	INT4 Q8 FP16	78 tok/s 47 tok/s 24 tok/s	~836 ms ~844 ms ~935 ms
-	Falcon3-7B	7B	INT4 Q8 FP16	74 tok/s 46 tok/s 22 tok/s	~836 ms ~844 ms ~1.0s
-	Hy-MT2 7B	7B	INT4 Q8 FP16	74 tok/s 46 tok/s 22 tok/s	~836 ms ~844 ms ~1.0s
-	Mistral-7B-v0.1	7.3B	INT4 Q8 FP16	72 tok/s 44 tok/s 22 tok/s	~870 ms ~878 ms ~1.1s
-	LensVLM 9B	9B	INT4 Q8	61 tok/s 37 tok/s	~1.1s ~1.1s
-	MiMo V2.6 Distill Qwen 9B	9B	INT4 Q8	61 tok/s 37 tok/s	~1.1s ~1.1s
-	ChatGLM3-6B-32K	6B	INT4 Q8 FP16	59 tok/s 42 tok/s 24 tok/s	~726 ms ~733 ms ~812 ms
-	Yi-6B	6B	INT4 Q8 FP16	59 tok/s 42 tok/s 24 tok/s	~726 ms ~733 ms ~812 ms
-	Falcon3-10B	10B	INT4 Q8	56 tok/s 33 tok/s	~1.2s ~1.2s
-	Falcon2-11B	11B	INT4 Q8	54 tok/s 31 tok/s	~1.3s ~1.3s
-	Hunyuan Lite	7B	INT4 Q8	53 tok/s 37 tok/s	~841 ms ~849 ms
-	Kimi-VL-A3B-Instruct	16B (3B active)	INT4	53 tok/s	~490 ms
-	OLMo 3 7B Base	7B	INT4 Q8	53 tok/s 37 tok/s	~841 ms ~849 ms
-	SEA-LION-7B	7.1B	INT4 Q8	53 tok/s 37 tok/s	~853 ms ~861 ms
-	SEA-LION-7B-Instruct	7.1B	INT4 Q8	53 tok/s 37 tok/s	~853 ms ~861 ms
-	Sahabat-AI-Llama3-8B-Instruct	8B	INT4 Q8	48 tok/s 34 tok/s	~956 ms ~965 ms
-	Typhoon-2-8B	8B	INT4 Q8	48 tok/s 34 tok/s	~956 ms ~965 ms
-	GLM-4-9B	9B	INT4 Q8	44 tok/s 29 tok/s	~1.1s ~1.2s
-	GLM-4-9B-Chat	9B	INT4 Q8	44 tok/s 29 tok/s	~1.1s ~1.2s
-	GLM-4-9B-Chat-1M	9B	INT4 Q8	44 tok/s 29 tok/s	~1.1s ~1.2s
-	Yi-9B	9B	INT4 Q8	44 tok/s 29 tok/s	~1.1s ~1.2s
-	Sahabat-AI-Gemma2-9B	9.2B	INT4 Q8	43 tok/s 28 tok/s	~1.1s ~1.2s
-	Sahabat-AI-Gemma2-9B-Instruct	9.2B	INT4 Q8	43 tok/s 28 tok/s	~1.1s ~1.2s
-	GreenMind-14B-R1	14B	INT4	31 tok/s	~1.7s

NVIDIA RTX 5060 Ti (16GB)

VRAM Scaling by Context Length

Best Models to Run on NVIDIA RTX 5060 Ti (16GB)

Inference Capacity

Fine-Tuning Capacity

Workload Recommendations

Frequently Asked Questions