What are the best models to run on NVIDIA A2 (16GB)?

Based on model rankings and 16 GB usable VRAM: Top Overall: Qwen 3.8 27B (INT4) ~9 tok/s. Top Coding: Qwen3.5-27B (INT4) ~9 tok/s. Optimal Daily Driver: Phi-4 Reasoning Plus (INT4) ~14 tok/s. Maximum Model Size: ERNIE-4.5-VL-28B-A3B (INT4) ~55 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 A2 (16GB) (October 2026)

Rank	Model	Parameters	Precision	TPS (Approx.)	TTFT
#33	Qwen 3.8 27B	27B	INT4	9 tok/s	~21.8s
#83	Qwen3.5-27B	27B	INT4	9 tok/s	~21.8s
#100	Phi-4 Reasoning Plus	14B	INT4	14 tok/s	~9.8s
#101	MiMo V2 Flash	15B (309B active)	INT4	1 tok/s	~220.2s
#108	Gemma 4 26B A4B	25.2B (3.8B active)	INT4	51 tok/s	~3.6s
#109	Gemma 4 12B	11.95B	INT4 Q8	16 tok/s 9 tok/s	~8.3s ~9.9s
#113	Qwen3.5-9B	9B	INT4 Q8	29 tok/s 17 tok/s	~6.3s ~6.3s
#118	K2 Horizon 7B	7B	INT4 Q8 FP16	37 tok/s 21 tok/s 10 tok/s	~4.9s ~5.0s ~5.9s
#128	NVIDIA Nemotron 3 Nano 30B-A3B	3.5B (30B active)	INT4 Q8 FP16	9 tok/s 5 tok/s 3 tok/s	~19.9s ~20.0s ~20.1s
#132	Qwen3.5-4B	4B	INT4 Q8 FP16	61 tok/s 36 tok/s 19 tok/s	~2.9s ~2.9s ~2.9s
#136	GPT-OSS 20B	21B (3.6B active)	INT4	20 tok/s	~3.7s
#146	Granite 4.2 8B	8B	INT4 Q8	33 tok/s 19 tok/s	~5.6s ~5.6s
#150	Gemma 4 E4B	8B	INT4 Q8	33 tok/s 19 tok/s	~5.6s ~5.6s
#158	GLM-4V	9B	INT4 Q8	20 tok/s 13 tok/s	~6.3s ~6.9s
#159	Gemma 3 27B	27B	INT4	9 tok/s	~21.8s
#160	Phi-4	14B	INT4 Q8	19 tok/s 10 tok/s	~9.7s ~11.5s
#169	OLMo 3 7B Think	7B	INT4 Q8	25 tok/s 17 tok/s	~4.9s ~5.0s
#172	DeepSeek-R1 14B	14B	INT4 Q8	20 tok/s 10 tok/s	~9.7s ~11.5s
#173	Ministral 3 14B	14B	INT4	14 tok/s	~9.8s
#177	Gemma 3 12B	12B	INT4 Q8	22 tok/s 12 tok/s	~8.4s ~9.1s
#181	Mistral-Small-2501	24B	INT4	11 tok/s	~17.9s
#182	Ministral 3 8B	8B	INT4 Q8	23 tok/s 15 tok/s	~5.6s ~5.6s
#183	Qwen3.5-2B	2B	INT4 Q8 FP16	106 tok/s 66 tok/s 36 tok/s	~1.5s ~1.5s ~1.5s
#184	MiniCPM5-2B	2B	INT4 Q8 FP16	106 tok/s 66 tok/s 36 tok/s	~1.5s ~1.5s ~1.5s
#185	Qwen2.5-14B	14B	INT4 Q8	19 tok/s 10 tok/s	~9.7s ~11.5s
#186	Gemma 2 27B	27B	INT4	9 tok/s	~21.8s
#188	Gemma 4 E2B	5.1B	INT4 Q8 FP16	49 tok/s 29 tok/s 15 tok/s	~3.6s ~3.6s ~3.7s
#189	Qwen3-4B	4B	INT4 Q8 FP16	61 tok/s 36 tok/s 19 tok/s	~2.9s ~2.9s ~2.9s
#190	DeepSeek-R1 8B	8B	INT4 Q8	34 tok/s 19 tok/s	~5.6s ~5.6s
#193	Ministral 3 3B	3B	INT4 Q8 FP16	46 tok/s 34 tok/s 21 tok/s	~2.2s ~2.2s ~2.2s
#195	Qwen3-14B	14B	INT4 Q8	19 tok/s 10 tok/s	~9.7s ~11.5s
#197	Gemma 2 9B	9B	INT4 Q8	29 tok/s 17 tok/s	~6.3s ~6.3s
#198	Qwen2.5-7B	7B	INT4 Q8 FP16	37 tok/s 21 tok/s 10 tok/s	~4.9s ~5.0s ~5.9s
#199	Qwen3-8B	8B	INT4 Q8	33 tok/s 19 tok/s	~5.6s ~5.6s
#200	Gemma 3 4B	4B	INT4 Q8 FP16	61 tok/s 36 tok/s 19 tok/s	~2.9s ~2.9s ~2.9s
#201	DeepSeek-R1 7B	7B	INT4 Q8 FP16	38 tok/s 22 tok/s 11 tok/s	~4.9s ~4.9s ~5.4s
#202	Llama 3.1 8B	8B	INT4 Q8	33 tok/s 19 tok/s	~5.6s ~5.6s
#204	Qwen3-1.7B	1.7B	INT4 Q8 FP16	121 tok/s 77 tok/s 42 tok/s	~1.3s ~1.3s ~1.3s
#206	Gemma 3 270M	0.27B	INT4 Q8 FP16	299 tok/s 247 tok/s 175 tok/s	~203 ms ~204 ms ~205 ms
#208	Llama 3 8B	8B	INT4 Q8	33 tok/s 19 tok/s	~5.6s ~5.6s
#209	Qwen3-0.6B	0.6B	INT4 Q8 FP16	259 tok/s 180 tok/s 108 tok/s	~457 ms ~459 ms ~463 ms
#210	Phi-4-Mini	3.8B	INT4 Q8 FP16	63 tok/s 38 tok/s 20 tok/s	~2.8s ~2.8s ~2.8s
#212	Ministral-8B-2410	8B	INT4 Q8	33 tok/s 19 tok/s	~5.6s ~5.6s
#213	DeepSeek-R1 1.5B	1.5B	INT4 Q8 FP16	133 tok/s 85 tok/s 47 tok/s	~1.2s ~1.2s ~1.2s
#214	Llama 3.2 3B	3B	INT4 Q8 FP16	77 tok/s 47 tok/s 25 tok/s	~2.2s ~2.2s ~2.2s
#215	Qwen3.5-0.8B	0.8B	INT4 Q8 FP16	213 tok/s 144 tok/s 84 tok/s	~620 ms ~622 ms ~627 ms
#216	Phi-3-mini	3.8B	INT4 Q8 FP16	63 tok/s 38 tok/s 20 tok/s	~2.8s ~2.8s ~2.8s
#217	Gemma 3n E2B IT	6B (2B active)	INT4 Q8 FP16	46 tok/s 38 tok/s 24 tok/s	~1.6s ~1.7s ~1.8s
#218	Mistral-7B-Instruct-v0.1	7.3B	INT4 Q8 FP16	36 tok/s 20 tok/s 10 tok/s	~5.1s ~5.2s ~6.1s
#219	Llama 3.2 1B	1B	INT4 Q8 FP16	179 tok/s 119 tok/s 68 tok/s	~789 ms ~792 ms ~798 ms
#220	Gemma 2 2B	2B	INT4 Q8 FP16	106 tok/s 66 tok/s 36 tok/s	~1.5s ~1.5s ~1.5s
#221	Phi-3-medium	14B	INT4 Q8	19 tok/s 10 tok/s	~9.7s ~11.5s
#222	OLMo 3 7B Instruct	7B	INT4 Q8	25 tok/s 17 tok/s	~4.9s ~5.0s
#224	Qwen2-7B	7B	INT4 Q8 FP16	37 tok/s 21 tok/s 10 tok/s	~4.9s ~5.0s ~5.9s
#225	Phi-3-small	7B	INT4 Q8 FP16	37 tok/s 21 tok/s 10 tok/s	~4.9s ~5.0s ~5.9s
#226	Gemma 3 1B	1B	INT4 Q8 FP16	179 tok/s 119 tok/s 68 tok/s	~789 ms ~792 ms ~798 ms
#227	Mistral-7B-Instruct-v0.2	7.3B	INT4 Q8 FP16	36 tok/s 20 tok/s 10 tok/s	~5.1s ~5.2s ~6.1s
#229	Gemma 1 7B	7B	INT4 Q8	25 tok/s 17 tok/s	~4.9s ~5.0s
#230	Gemma 1 2B	2B	INT4 Q8 FP16	117 tok/s 70 tok/s 37 tok/s	~1.5s ~1.5s ~1.5s
#231	ChatGLM3-6B	6B	INT4 Q8 FP16	28 tok/s 19 tok/s 11 tok/s	~4.3s ~4.3s ~4.7s
#232	ChatGLM2-6B	6B	INT4 Q8 FP16	28 tok/s 19 tok/s 11 tok/s	~4.3s ~4.3s ~4.7s
#233	ChatGLM-6B	6B	INT4 Q8 FP16	28 tok/s 19 tok/s 11 tok/s	~4.3s ~4.3s ~4.7s
Unranked Models (Sorted by Speed)
-	Qwen2-0.5B	0.5B	INT4 Q8 FP16	290 tok/s 206 tok/s 125 tok/s	~378 ms ~380 ms ~383 ms
-	Qwen2.5-0.5B	0.5B	INT4 Q8 FP16	290 tok/s 206 tok/s 125 tok/s	~378 ms ~380 ms ~383 ms
-	ERNIE-4.5-0.3B	0.3B	INT4 Q8 FP16	278 tok/s 229 tok/s 160 tok/s	~227 ms ~227 ms ~229 ms
-	ERNIE-4.5-0.3B-Base	0.3B	INT4 Q8 FP16	278 tok/s 229 tok/s 160 tok/s	~227 ms ~227 ms ~229 ms
-	Falcon-1B	1B	INT4 Q8 FP16	198 tok/s 127 tok/s 71 tok/s	~788 ms ~791 ms ~797 ms
-	Falcon3-1B	1B	INT4 Q8 FP16	179 tok/s 119 tok/s 68 tok/s	~789 ms ~792 ms ~798 ms
-	Qwen2-1.5B	1.5B	INT4 Q8 FP16	133 tok/s 85 tok/s 47 tok/s	~1.2s ~1.2s ~1.2s
-	Qwen2.5-1.5B	1.5B	INT4 Q8 FP16	133 tok/s 85 tok/s 47 tok/s	~1.2s ~1.2s ~1.2s
-	Spark X2.5 1.7B	1.7B	INT4 Q8 FP16	121 tok/s 77 tok/s 42 tok/s	~1.3s ~1.3s ~1.3s
-	Hy-MT2 1.8B	1.8B	INT4 Q8 FP16	116 tok/s 73 tok/s 40 tok/s	~1.4s ~1.4s ~1.4s
-	Falcon-3B	3B	INT4 Q8 FP16	83 tok/s 49 tok/s 25 tok/s	~2.2s ~2.2s ~2.2s
-	CroissantLLM Base	1.3B	INT4 Q8 FP16	81 tok/s 65 tok/s 42 tok/s	~1.0s ~1.0s ~1.0s
-	Phi-1	1.3B	INT4 Q8 FP16	81 tok/s 65 tok/s 42 tok/s	~1.0s ~1.0s ~1.0s
-	Phi-1.5	1.3B	INT4 Q8 FP16	81 tok/s 65 tok/s 42 tok/s	~1.0s ~1.0s ~1.0s
-	DeepSeek-R1 3B	3B	INT4 Q8 FP16	79 tok/s 47 tok/s 25 tok/s	~2.2s ~2.2s ~2.2s
-	Falcon3-3B	3B	INT4 Q8 FP16	77 tok/s 47 tok/s 25 tok/s	~2.2s ~2.2s ~2.2s
-	Qwen2.5-3B	3B	INT4 Q8 FP16	77 tok/s 47 tok/s 25 tok/s	~2.2s ~2.2s ~2.2s
-	ERNIE-4.5-21B-A3B	21B (3B active)	INT4	61 tok/s	~2.9s
-	ERNIE-4.5-21B-A3B-Base	21B (3B active)	INT4	61 tok/s	~2.9s
-	Spark X2.5 4B	4B	INT4 Q8 FP16	61 tok/s 36 tok/s 19 tok/s	~2.9s ~2.9s ~2.9s
-	ERNIE-4.5-VL-28B-A3B	28B (3B active)	INT4	55 tok/s	~3.3s
-	ERNIE-4.5-VL-28B-A3B-Base	28B (3B active)	INT4	55 tok/s	~3.3s
-	Phi-2	2.7B	INT4 Q8 FP16	49 tok/s 37 tok/s 23 tok/s	~2.0s ~2.0s ~2.0s
-	MaLLaM-3B	3B	INT4 Q8 FP16	46 tok/s 34 tok/s 21 tok/s	~2.2s ~2.2s ~2.2s
-	SmolLM3 3B	3B	INT4 Q8 FP16	46 tok/s 34 tok/s 21 tok/s	~2.2s ~2.2s ~2.2s
-	Falcon-7B	7B	INT4 Q8 FP16	39 tok/s 22 tok/s 11 tok/s	~4.9s ~4.9s ~5.4s
-	Falcon3-7B	7B	INT4 Q8 FP16	37 tok/s 21 tok/s 10 tok/s	~4.9s ~5.0s ~5.9s
-	Hy-MT2 7B	7B	INT4 Q8 FP16	37 tok/s 21 tok/s 10 tok/s	~4.9s ~5.0s ~5.9s
-	Mistral-7B-v0.1	7.3B	INT4 Q8 FP16	36 tok/s 20 tok/s 10 tok/s	~5.1s ~5.2s ~6.1s
-	LensVLM 9B	9B	INT4 Q8	29 tok/s 17 tok/s	~6.3s ~6.3s
-	MiMo V2.6 Distill Qwen 9B	9B	INT4 Q8	29 tok/s 17 tok/s	~6.3s ~6.3s
-	ChatGLM3-6B-32K	6B	INT4 Q8 FP16	28 tok/s 19 tok/s 11 tok/s	~4.3s ~4.3s ~4.7s
-	Yi-6B	6B	INT4 Q8 FP16	28 tok/s 19 tok/s 11 tok/s	~4.3s ~4.3s ~4.7s
-	Falcon3-10B	10B	INT4 Q8	26 tok/s 15 tok/s	~7.0s ~7.0s
-	Falcon2-11B	11B	INT4 Q8	25 tok/s 14 tok/s	~7.7s ~7.7s
-	Hunyuan Lite	7B	INT4 Q8	25 tok/s 17 tok/s	~4.9s ~5.0s
-	Kimi-VL-A3B-Instruct	16B (3B active)	INT4	25 tok/s	~2.8s
-	OLMo 3 7B Base	7B	INT4 Q8	25 tok/s 17 tok/s	~4.9s ~5.0s
-	SEA-LION-7B	7.1B	INT4 Q8	25 tok/s 17 tok/s	~5.0s ~5.0s
-	SEA-LION-7B-Instruct	7.1B	INT4 Q8	25 tok/s 17 tok/s	~5.0s ~5.0s
-	Sahabat-AI-Llama3-8B-Instruct	8B	INT4 Q8	23 tok/s 15 tok/s	~5.6s ~5.6s
-	Typhoon-2-8B	8B	INT4 Q8	23 tok/s 15 tok/s	~5.6s ~5.6s
-	GLM-4-9B	9B	INT4 Q8	20 tok/s 13 tok/s	~6.3s ~6.9s
-	GLM-4-9B-Chat	9B	INT4 Q8	20 tok/s 13 tok/s	~6.3s ~6.9s
-	GLM-4-9B-Chat-1M	9B	INT4 Q8	20 tok/s 13 tok/s	~6.3s ~6.9s
-	Sahabat-AI-Gemma2-9B	9.2B	INT4 Q8	20 tok/s 13 tok/s	~6.5s ~7.0s
-	Sahabat-AI-Gemma2-9B-Instruct	9.2B	INT4 Q8	20 tok/s 13 tok/s	~6.5s ~7.0s
-	Yi-9B	9B	INT4 Q8	20 tok/s 13 tok/s	~6.3s ~6.9s
-	GreenMind-14B-R1	14B	INT4	14 tok/s	~9.8s

NVIDIA A2 (16GB)

VRAM Scaling by Context Length

Best Models to Run on NVIDIA A2 (16GB)

Inference Capacity

Fine-Tuning Capacity

Workload Recommendations

Frequently Asked Questions