What are the best models to run on NVIDIA RTX 3070 Ti (8GB)?

Based on model rankings and 8 GB usable VRAM: Top Overall: Qwen3.5-9B (INT4) ~78 tok/s. Top Coding: K2 Horizon 7B (INT4) ~94 tok/s. Optimal Daily Driver: Granite 4.2 8B (INT4) ~85 tok/s. Maximum Model Size: HunyuanVideo 1.5 720P T2V (INT4) ~52 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 LLMs to Run on NVIDIA RTX 3070 Ti (8GB)

Rank	Model	Parameters	Precision	TPS (Approx.)	TTFT
#125	Qwen3.5-9B	9B	INT4	78 tok/s	~1.2s
#128	K2 Horizon 7B	7B	INT4	94 tok/s	~906 ms
#140	Qwen3.5-4B	4B	INT4 Q8	136 tok/s 92 tok/s	~533 ms ~537 ms
#150	NVIDIA Nemotron 3 Nano 30B-A3B	3.5B (30B active)	INT4 Q8	27 tok/s 15 tok/s	~3.6s ~4.0s
#158	Granite 4.2 8B	8B	INT4	85 tok/s	~1.0s
#159	Gemma 4 E4B	8B	INT4	85 tok/s	~1.0s
#178	OLMo 3 7B Think	7B	INT4	65 tok/s	~988 ms
#186	Gemma 3 12B	12B	INT4	56 tok/s	~1.8s
#189	Ministral 3 8B	8B	INT4	56 tok/s	~1.2s
#191	MiniCPM5-2B	2B	INT4 Q8 FP16	194 tok/s 145 tok/s 93 tok/s	~286 ms ~288 ms ~292 ms
#192	Qwen3.5-2B	2B	INT4 Q8 FP16	194 tok/s 145 tok/s 93 tok/s	~286 ms ~288 ms ~292 ms
#200	Gemma 4 E2B	5.1B	INT4 Q8	117 tok/s 73 tok/s	~670 ms ~732 ms
#202	DeepSeek-R1 8B	8B	INT4	87 tok/s	~1.0s
#204	Qwen3-4B	4B	INT4 Q8	136 tok/s 92 tok/s	~533 ms ~537 ms
#205	Ministral 3 3B	3B	INT4 Q8	112 tok/s 88 tok/s	~412 ms ~414 ms
#207	Gemma 2 9B	9B	INT4	78 tok/s	~1.2s
#208	Qwen3.5-0.8B	0.8B	INT4 Q8 FP16	271 tok/s 228 tok/s 169 tok/s	~120 ms ~121 ms ~122 ms
#210	Gemma 3 4B	4B	INT4 Q8	136 tok/s 92 tok/s	~533 ms ~537 ms
#211	Qwen3-8B	8B	INT4	85 tok/s	~1.0s
#213	DeepSeek-R1 7B	7B	INT4 Q8	96 tok/s 54 tok/s	~906 ms ~1.1s
#214	Qwen3-1.7B	1.7B	INT4 Q8 FP16	208 tok/s 159 tok/s 105 tok/s	~246 ms ~247 ms ~250 ms
#215	Llama 3.1 8B	8B	INT4	85 tok/s	~1.0s
#216	Gemma 3 270M	0.27B	INT4 Q8 FP16	306 tok/s 287 tok/s 249 tok/s	~44 ms ~44 ms ~45 ms
#218	Qwen3-0.6B	0.6B	INT4 Q8 FP16	292 tok/s 253 tok/s 196 tok/s	~90 ms ~91 ms ~92 ms
#219	Llama 3 8B	8B	INT4	85 tok/s	~1.0s
#221	Phi-4-Mini	3.8B	INT4 Q8	140 tok/s 96 tok/s	~509 ms ~512 ms
#223	Qwen2.5-7B	7B	INT4	94 tok/s	~906 ms
#224	Ministral-8B-2410	8B	INT4	85 tok/s	~1.0s
#225	DeepSeek-R1 1.5B	1.5B	INT4 Q8 FP16	220 tok/s 171 tok/s 114 tok/s	~218 ms ~219 ms ~222 ms
#226	Llama 3.2 3B	3B	INT4 Q8 FP16	160 tok/s 113 tok/s 65 tok/s	~409 ms ~412 ms ~453 ms
#228	Phi-3-mini	3.8B	INT4 Q8	140 tok/s 96 tok/s	~509 ms ~512 ms
#229	Gemma 3n E2B IT	6B (2B active)	INT4	106 tok/s	~335 ms
#230	Mistral-7B-Instruct-v0.1	7.3B	INT4	91 tok/s	~943 ms
#231	Llama 3.2 1B	1B	INT4 Q8 FP16	252 tok/s 207 tok/s 148 tok/s	~151 ms ~152 ms ~154 ms
#232	Gemma 2 2B	2B	INT4 Q8 FP16	194 tok/s 145 tok/s 93 tok/s	~286 ms ~288 ms ~292 ms
#234	OLMo 3 7B Instruct	7B	INT4	65 tok/s	~988 ms
#236	Qwen2-7B	7B	INT4	94 tok/s	~906 ms
#237	Phi-3-small	7B	INT4	94 tok/s	~906 ms
#238	Gemma 3 1B	1B	INT4 Q8 FP16	252 tok/s 207 tok/s 148 tok/s	~151 ms ~152 ms ~154 ms
#239	Mistral-7B-Instruct-v0.2	7.3B	INT4	91 tok/s	~943 ms
#241	Gemma 1 7B	7B	INT4	65 tok/s	~988 ms
#242	Gemma 1 2B	2B	INT4 Q8 FP16	205 tok/s 150 tok/s 95 tok/s	~286 ms ~287 ms ~291 ms
#243	ChatGLM3-6B	6B	INT4	72 tok/s	~853 ms
#244	ChatGLM2-6B	6B	INT4	72 tok/s	~853 ms
#245	ChatGLM-6B	6B	INT4	72 tok/s	~853 ms
Unranked Models (Sorted by Speed)
-	DINOv3 ViT-L/16	0.3B	INT4 Q8 FP16	327 tok/s 301 tok/s 256 tok/s	~48 ms ~48 ms ~49 ms
-	Qwen2-0.5B	0.5B	INT4 Q8 FP16	303 tok/s 267 tok/s 212 tok/s	~76 ms ~76 ms ~77 ms
-	Qwen2.5-0.5B	0.5B	INT4 Q8 FP16	303 tok/s 267 tok/s 212 tok/s	~76 ms ~76 ms ~77 ms
-	ERNIE-4.5-0.3B	0.3B	INT4 Q8 FP16	298 tok/s 279 tok/s 240 tok/s	~49 ms ~49 ms ~49 ms
-	ERNIE-4.5-0.3B-Base	0.3B	INT4 Q8 FP16	298 tok/s 279 tok/s 240 tok/s	~49 ms ~49 ms ~49 ms
-	Liquid D1-Omni 600M	0.6B	INT4 Q8 FP16	292 tok/s 253 tok/s 196 tok/s	~90 ms ~91 ms ~92 ms
-	PixArt-α XL 2 1024-MS	0.61B	INT4 Q8 FP16	291 tok/s 252 tok/s 194 tok/s	~92 ms ~92 ms ~93 ms
-	PixArt-Σ XL 2 1024-MS	0.61B	INT4 Q8 FP16	291 tok/s 252 tok/s 194 tok/s	~92 ms ~92 ms ~93 ms
-	Nemotron 3.5 Parse	0.63B	INT4 Q8 FP16	288 tok/s 249 tok/s 191 tok/s	~95 ms ~96 ms ~97 ms
-	SD 2.1 Turbo	0.86B	INT4 Q8 FP16	265 tok/s 221 tok/s 162 tok/s	~129 ms ~130 ms ~131 ms
-	Stable Diffusion 1.4	0.86B	INT4 Q8 FP16	265 tok/s 221 tok/s 162 tok/s	~129 ms ~130 ms ~131 ms
-	Stable Diffusion 2.1	0.86B	INT4 Q8 FP16	265 tok/s 221 tok/s 162 tok/s	~129 ms ~130 ms ~131 ms
-	Falcon-1B	1B	INT4 Q8 FP16	263 tok/s 214 tok/s 151 tok/s	~151 ms ~152 ms ~153 ms
-	Falcon3-1B	1B	INT4 Q8 FP16	252 tok/s 207 tok/s 148 tok/s	~151 ms ~152 ms ~154 ms
-	MiniCPM-V 4.7 1B	1B	INT4 Q8 FP16	252 tok/s 207 tok/s 148 tok/s	~151 ms ~152 ms ~154 ms
-	Kandinsky 2.2 Decoder	1.22B	INT4 Q8 FP16	237 tok/s 189 tok/s 131 tok/s	~180 ms ~182 ms ~184 ms
-	Wan 2.1 T2V 1.3B	1.3B	INT4 Q8 FP16	232 tok/s 184 tok/s 126 tok/s	~191 ms ~192 ms ~194 ms
-	Qwen2-1.5B	1.5B	INT4 Q8 FP16	220 tok/s 171 tok/s 114 tok/s	~218 ms ~219 ms ~222 ms
-	Qwen2.5-1.5B	1.5B	INT4 Q8 FP16	220 tok/s 171 tok/s 114 tok/s	~218 ms ~219 ms ~222 ms
-	SVD Image-to-Video XT	1.5B	INT4 Q8 FP16	220 tok/s 171 tok/s 114 tok/s	~218 ms ~219 ms ~222 ms
-	SVD Image-to-Video XT 1.1	1.5B	INT4 Q8 FP16	220 tok/s 171 tok/s 114 tok/s	~218 ms ~219 ms ~222 ms
-	LFM3 1.7B	1.7B	INT4 Q8 FP16	208 tok/s 159 tok/s 105 tok/s	~246 ms ~247 ms ~250 ms
-	LFM3 1.7B Base	1.7B	INT4 Q8 FP16	208 tok/s 159 tok/s 105 tok/s	~246 ms ~247 ms ~250 ms
-	Spark X2.5 1.7B	1.7B	INT4 Q8 FP16	208 tok/s 159 tok/s 105 tok/s	~246 ms ~247 ms ~250 ms
-	Hy-MT2 1.8B	1.8B	INT4 Q8 FP16	204 tok/s 154 tok/s 100 tok/s	~258 ms ~260 ms ~263 ms
-	CogVideoX 2B	2B	INT4 Q8 FP16	194 tok/s 145 tok/s 93 tok/s	~286 ms ~288 ms ~292 ms
-	LFM3 Audio 2B	2B	INT4 Q8 FP16	194 tok/s 145 tok/s 93 tok/s	~286 ms ~288 ms ~292 ms
-	LFM3 Omni 2B	2B	INT4 Q8 FP16	194 tok/s 145 tok/s 93 tok/s	~286 ms ~288 ms ~292 ms
-	LFM3 VL 2B	2B	INT4 Q8 FP16	194 tok/s 145 tok/s 93 tok/s	~286 ms ~288 ms ~292 ms
-	Liquid D1 2B	2B	INT4 Q8 FP16	194 tok/s 145 tok/s 93 tok/s	~286 ms ~288 ms ~292 ms
-	LTX-Video 0.9.1	2B	INT4 Q8 FP16	194 tok/s 145 tok/s 93 tok/s	~286 ms ~288 ms ~292 ms
-	Moondream 3.1	9B (2B active)	INT4	194 tok/s	~321 ms
-	Stable Diffusion 3 Medium	2B	INT4 Q8 FP16	194 tok/s 145 tok/s 93 tok/s	~286 ms ~288 ms ~292 ms
-	Kandinsky 3.0	2.1B	INT4 Q8 FP16	190 tok/s 141 tok/s 90 tok/s	~298 ms ~300 ms ~304 ms
-	LTX-2	2.2B	INT4 Q8 FP16	186 tok/s 137 tok/s 87 tok/s	~311 ms ~313 ms ~317 ms
-	SDXL 1.0 Refiner	2.31B	INT4 Q8 FP16	182 tok/s 133 tok/s 84 tok/s	~324 ms ~326 ms ~331 ms
-	Stable Diffusion 3.5 Medium	2.5B	INT4 Q8 FP16	175 tok/s 127 tok/s 79 tok/s	~348 ms ~350 ms ~355 ms
-	SDXL 1.0 Base	2.56B	INT4 Q8 FP16	173 tok/s 125 tok/s 73 tok/s	~355 ms ~357 ms ~393 ms
-	SDXL Turbo	2.56B	INT4 Q8 FP16	173 tok/s 125 tok/s 73 tok/s	~355 ms ~357 ms ~393 ms
-	Falcon-3B	3B	INT4 Q8 FP16	168 tok/s 116 tok/s 66 tok/s	~409 ms ~412 ms ~453 ms
-	CroissantLLM Base	1.3B	INT4 Q8 FP16	166 tok/s 142 tok/s 105 tok/s	~192 ms ~193 ms ~196 ms
-	Phi-1	1.3B	INT4 Q8 FP16	166 tok/s 142 tok/s 105 tok/s	~192 ms ~193 ms ~196 ms
-	Phi-1.5	1.3B	INT4 Q8 FP16	166 tok/s 142 tok/s 105 tok/s	~192 ms ~193 ms ~196 ms
-	DeepSeek-R1 3B	3B	INT4 Q8 FP16	162 tok/s 114 tok/s 65 tok/s	~409 ms ~412 ms ~453 ms
-	Falcon3-3B	3B	INT4 Q8 FP16	160 tok/s 113 tok/s 65 tok/s	~409 ms ~412 ms ~453 ms
-	LFM2-VL 3B	3B	INT4 Q8 FP16	160 tok/s 113 tok/s 65 tok/s	~409 ms ~412 ms ~453 ms
-	Liquid D1 3B	3B	INT4 Q8 FP16	160 tok/s 113 tok/s 65 tok/s	~409 ms ~412 ms ~453 ms
-	Liquid D1-VL 3B	3B	INT4 Q8 FP16	160 tok/s 113 tok/s 65 tok/s	~409 ms ~412 ms ~453 ms
-	Liquid LFM2-VL 3B D1	3B	INT4 Q8 FP16	160 tok/s 113 tok/s 65 tok/s	~409 ms ~412 ms ~453 ms
-	Qwen2.5-3B	3B	INT4 Q8 FP16	160 tok/s 113 tok/s 65 tok/s	~409 ms ~412 ms ~453 ms
-	Mellum 2.1 12B A2.5B Thinking	12B (2.5B active)	INT4	146 tok/s	~469 ms
-	FLUX.2 Klein 4B	4B	INT4 Q8	136 tok/s 92 tok/s	~533 ms ~537 ms
-	FrogNano 4B	4B	INT4 Q8	136 tok/s 92 tok/s	~533 ms ~537 ms
-	Mage-VL Cowork	4B	INT4 Q8	136 tok/s 92 tok/s	~533 ms ~537 ms
-	Spark X2.5 4B	4B	INT4 Q8	136 tok/s 92 tok/s	~533 ms ~537 ms
-	EmbeddingGemma 2	2B	INT4 Q8 FP16	131 tok/s 109 tok/s 73 tok/s	~288 ms ~290 ms ~319 ms
-	CogVideoX 1.5 5B	5B	INT4 Q8	119 tok/s 74 tok/s	~658 ms ~719 ms
-	CogVideoX 5B	5B	INT4 Q8	119 tok/s 74 tok/s	~658 ms ~719 ms
-	Wan 2.2 TI2V 5B	5B	INT4 Q8	119 tok/s 74 tok/s	~658 ms ~719 ms
-	Phi-2	2.7B	INT4 Q8 FP16	117 tok/s 93 tok/s 57 tok/s	~375 ms ~377 ms ~448 ms
-	MaLLaM-3B	3B	INT4 Q8	112 tok/s 88 tok/s	~412 ms ~414 ms
-	SmolLM3 3B	3B	INT4 Q8	112 tok/s 88 tok/s	~412 ms ~414 ms
-	Falcon-7B	7B	INT4 Q8	98 tok/s 55 tok/s	~906 ms ~1.1s
-	AuraFlow v0.2	6.8B	INT4 Q8	96 tok/s 55 tok/s	~881 ms ~1.0s
-	AuraFlow v0.3	6.8B	INT4 Q8	96 tok/s 55 tok/s	~881 ms ~1.0s
-	Falcon3-7B	7B	INT4	94 tok/s	~906 ms
-	Hy-MT2 7B	7B	INT4	94 tok/s	~906 ms
-	Mistral-7B-v0.1	7.3B	INT4	91 tok/s	~943 ms
-	Youtu Parsing Omni	8B	INT4	87 tok/s	~1.0s
-	Stable Diffusion 3.5 Large	8.1B	INT4	85 tok/s	~1.0s
-	Stable Diffusion 3.5 Large Turbo	8.1B	INT4	85 tok/s	~1.0s
-	FLUX.2 Klein 9B	9B	INT4	78 tok/s	~1.2s
-	LensVLM 9B	9B	INT4	78 tok/s	~1.2s
-	MiMo V2.6 Distill Qwen 9B	9B	INT4	78 tok/s	~1.2s
-	ChatGLM3-6B-32K	6B	INT4	72 tok/s	~853 ms
-	Yi-6B	6B	INT4	72 tok/s	~853 ms
-	Falcon3-10B	10B	INT4	68 tok/s	~1.4s
-	Mochi 1 Preview	10B	INT4	68 tok/s	~1.4s
-	Falcon2-11B	11B	INT4	66 tok/s	~1.5s
-	Hunyuan Lite	7B	INT4	65 tok/s	~988 ms
-	OLMo 3 7B Base	7B	INT4	65 tok/s	~988 ms
-	SEA-LION-7B	7.1B	INT4	65 tok/s	~1.0s
-	SEA-LION-7B-Instruct	7.1B	INT4	65 tok/s	~1.0s
-	FLUX.1 Canny Dev	11.9B	INT4	56 tok/s	~1.8s
-	FLUX.1 Depth Dev	11.9B	INT4	56 tok/s	~1.8s
-	FLUX.1 Dev	11.9B	INT4	56 tok/s	~1.8s
-	FLUX.1 Fill Dev	11.9B	INT4	56 tok/s	~1.8s
-	FLUX.1 Schnell	11.9B	INT4	56 tok/s	~1.8s
-	Sahabat-AI-Llama3-8B-Instruct	8B	INT4	56 tok/s	~1.2s
-	Typhoon-2-8B	8B	INT4	56 tok/s	~1.2s
-	HunyuanVideo 1.5 720P T2V	13B	INT4	52 tok/s	~1.9s

NVIDIA RTX 3070 Ti (8GB)

VRAM Scaling by Context Length

Best Models to Run on NVIDIA RTX 3070 Ti (8GB)

Inference Capacity

Fine-Tuning Capacity

Workload Recommendations

Frequently Asked Questions