What are the best models to run on NVIDIA RTX 5070 (12GB)?

Based on model rankings and 12 GB usable VRAM: Top Overall: Phi-4 Reasoning Plus (INT4) ~40 tok/s. Top Coding: K2 Horizon 7B (INT4) ~101 tok/s. Optimal Daily Driver: Qwen3.5-9B (INT4) ~84 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 5070 (12GB)

Rank	Model	Parameters	Precision	TPS (Approx.)	TTFT
#102	Phi-4 Reasoning Plus	14B	INT4	40 tok/s	~1.5s
#121	Qwen3.5-9B	9B	INT4 Q8	84 tok/s 50 tok/s	~820 ms ~898 ms
#127	K2 Horizon 7B	7B	INT4 Q8	101 tok/s 65 tok/s	~643 ms ~649 ms
#130	Gemma 4 12B	11.95B	INT4	47 tok/s	~1.2s
#136	Qwen3.5-4B	4B	INT4 Q8 FP16	145 tok/s 99 tok/s 59 tok/s	~380 ms ~383 ms ~390 ms
#140	GLM-4V	9B	INT4	62 tok/s	~825 ms
#145	NVIDIA Nemotron 3 Nano 30B-A3B	3.5B (30B active)	INT4 Q8 FP16	29 tok/s 17 tok/s 9 tok/s	~2.6s ~2.6s ~2.9s
#152	Granite 4.2 8B	8B	INT4 Q8	92 tok/s 55 tok/s	~731 ms ~800 ms
#157	Gemma 4 E4B	8B	INT4 Q8	92 tok/s 55 tok/s	~731 ms ~800 ms
#164	Phi-4	14B	INT4	59 tok/s	~1.3s
#176	DeepSeek-R1 14B	14B	INT4	61 tok/s	~1.3s
#177	Ministral 3 14B	14B	INT4	40 tok/s	~1.5s
#180	Gemma 3 12B	12B	INT4	67 tok/s	~1.1s
#185	Ministral 3 8B	8B	INT4 Q8	68 tok/s 43 tok/s	~735 ms ~869 ms
#187	OLMo 3 7B Think	7B	INT4 Q8	74 tok/s 51 tok/s	~647 ms ~707 ms
#188	Qwen3.5-2B	2B	INT4 Q8 FP16	203 tok/s 154 tok/s 100 tok/s	~205 ms ~206 ms ~210 ms
#189	MiniCPM5-2B	2B	INT4 Q8 FP16	203 tok/s 154 tok/s 100 tok/s	~205 ms ~206 ms ~210 ms
#190	Qwen2.5-14B	14B	INT4	59 tok/s	~1.3s
#193	Gemma 4 E2B	5.1B	INT4 Q8 FP16	125 tok/s 83 tok/s 43 tok/s	~476 ms ~480 ms ~573 ms
#195	Ministral 3 3B	3B	INT4 Q8 FP16	120 tok/s 95 tok/s 63 tok/s	~294 ms ~296 ms ~302 ms
#196	DeepSeek-R1 8B	8B	INT4 Q8	94 tok/s 59 tok/s	~731 ms ~737 ms
#198	Gemma 2 9B	9B	INT4 Q8	84 tok/s 50 tok/s	~820 ms ~898 ms
#201	Qwen3-4B	4B	INT4 Q8 FP16	145 tok/s 99 tok/s 59 tok/s	~380 ms ~383 ms ~390 ms
#202	Qwen3-14B	14B	INT4	59 tok/s	~1.3s
#203	Gemma 3 4B	4B	INT4 Q8 FP16	145 tok/s 99 tok/s 59 tok/s	~380 ms ~383 ms ~390 ms
#204	DeepSeek-R1 7B	7B	INT4 Q8	104 tok/s 66 tok/s	~643 ms ~649 ms
#206	Qwen3.5-0.8B	0.8B	INT4 Q8 FP16	278 tok/s 237 tok/s 178 tok/s	~87 ms ~88 ms ~89 ms
#207	Llama 3.1 8B	8B	INT4 Q8	92 tok/s 55 tok/s	~731 ms ~800 ms
#207	Qwen3-8B	8B	INT4 Q8	92 tok/s 55 tok/s	~731 ms ~800 ms
#212	Llama 3 8B	8B	INT4 Q8	92 tok/s 55 tok/s	~731 ms ~800 ms
#213	Qwen3-1.7B	1.7B	INT4 Q8 FP16	217 tok/s 168 tok/s 112 tok/s	~176 ms ~177 ms ~180 ms
#214	Gemma 3 270M	0.27B	INT4 Q8 FP16	311 tok/s 293 tok/s 257 tok/s	~34 ms ~34 ms ~34 ms
#216	Qwen3-0.6B	0.6B	INT4 Q8 FP16	298 tok/s 261 tok/s 205 tok/s	~66 ms ~67 ms ~68 ms
#217	Phi-4-Mini	3.8B	INT4 Q8 FP16	149 tok/s 103 tok/s 61 tok/s	~362 ms ~365 ms ~372 ms
#218	Qwen2.5-7B	7B	INT4 Q8	101 tok/s 65 tok/s	~643 ms ~649 ms
#220	Ministral-8B-2410	8B	INT4 Q8	92 tok/s 55 tok/s	~731 ms ~800 ms
#221	DeepSeek-R1 1.5B	1.5B	INT4 Q8 FP16	228 tok/s 180 tok/s 122 tok/s	~156 ms ~158 ms ~160 ms
#222	Llama 3.2 3B	3B	INT4 Q8 FP16	169 tok/s 121 tok/s 74 tok/s	~292 ms ~294 ms ~299 ms
#223	Phi-3-mini	3.8B	INT4 Q8 FP16	149 tok/s 103 tok/s 61 tok/s	~362 ms ~365 ms ~372 ms
#224	Gemma 3n E2B IT	6B (2B active)	INT4 Q8	119 tok/s 103 tok/s	~221 ms ~223 ms
#225	Gemma 2 2B	2B	INT4 Q8 FP16	203 tok/s 154 tok/s 100 tok/s	~205 ms ~206 ms ~210 ms
#226	Mistral-7B-Instruct-v0.1	7.3B	INT4 Q8	98 tok/s 63 tok/s	~669 ms ~675 ms
#227	Llama 3.2 1B	1B	INT4 Q8 FP16	260 tok/s 216 tok/s 157 tok/s	~109 ms ~110 ms ~112 ms
#228	Phi-3-medium	14B	INT4	59 tok/s	~1.3s
#230	OLMo 3 7B Instruct	7B	INT4 Q8	74 tok/s 51 tok/s	~647 ms ~707 ms
#231	Qwen2-7B	7B	INT4 Q8	101 tok/s 65 tok/s	~643 ms ~649 ms
#232	Phi-3-small	7B	INT4 Q8	101 tok/s 65 tok/s	~643 ms ~649 ms
#233	Mistral-7B-Instruct-v0.2	7.3B	INT4 Q8	98 tok/s 63 tok/s	~669 ms ~675 ms
#234	Gemma 3 1B	1B	INT4 Q8 FP16	260 tok/s 216 tok/s 157 tok/s	~109 ms ~110 ms ~112 ms
#236	Gemma 1 7B	7B	INT4 Q8	74 tok/s 51 tok/s	~647 ms ~707 ms
#237	Gemma 1 2B	2B	INT4 Q8 FP16	214 tok/s 159 tok/s 102 tok/s	~204 ms ~206 ms ~209 ms
#238	ChatGLM3-6B	6B	INT4 Q8	82 tok/s 60 tok/s	~559 ms ~563 ms
#239	ChatGLM2-6B	6B	INT4 Q8	82 tok/s 60 tok/s	~559 ms ~563 ms
#240	ChatGLM-6B	6B	INT4 Q8	82 tok/s 60 tok/s	~559 ms ~563 ms
Unranked Models (Sorted by Speed)
-	DINOv3 ViT-L/16	0.3B	INT4 Q8 FP16	331 tok/s 307 tok/s 264 tok/s	~36 ms ~37 ms ~37 ms
-	Qwen2-0.5B	0.5B	INT4 Q8 FP16	308 tok/s 275 tok/s 221 tok/s	~56 ms ~56 ms ~57 ms
-	Qwen2.5-0.5B	0.5B	INT4 Q8 FP16	308 tok/s 275 tok/s 221 tok/s	~56 ms ~56 ms ~57 ms
-	ERNIE-4.5-0.3B	0.3B	INT4 Q8 FP16	304 tok/s 285 tok/s 248 tok/s	~37 ms ~37 ms ~37 ms
-	ERNIE-4.5-0.3B-Base	0.3B	INT4 Q8 FP16	304 tok/s 285 tok/s 248 tok/s	~37 ms ~37 ms ~37 ms
-	Liquid D1-Omni 600M	0.6B	INT4 Q8 FP16	298 tok/s 261 tok/s 205 tok/s	~66 ms ~67 ms ~68 ms
-	Falcon-1B	1B	INT4 Q8 FP16	270 tok/s 223 tok/s 160 tok/s	~109 ms ~110 ms ~111 ms
-	Falcon3-1B	1B	INT4 Q8 FP16	260 tok/s 216 tok/s 157 tok/s	~109 ms ~110 ms ~112 ms
-	MiniCPM-V 4.7 1B	1B	INT4 Q8 FP16	260 tok/s 216 tok/s 157 tok/s	~109 ms ~110 ms ~112 ms
-	Qwen2-1.5B	1.5B	INT4 Q8 FP16	228 tok/s 180 tok/s 122 tok/s	~156 ms ~158 ms ~160 ms
-	Qwen2.5-1.5B	1.5B	INT4 Q8 FP16	228 tok/s 180 tok/s 122 tok/s	~156 ms ~158 ms ~160 ms
-	Spark X2.5 1.7B	1.7B	INT4 Q8 FP16	217 tok/s 168 tok/s 112 tok/s	~176 ms ~177 ms ~180 ms
-	Hy-MT2 1.8B	1.8B	INT4 Q8 FP16	213 tok/s 164 tok/s 108 tok/s	~185 ms ~186 ms ~189 ms
-	Falcon-3B	3B	INT4 Q8 FP16	177 tok/s 125 tok/s 75 tok/s	~291 ms ~294 ms ~299 ms
-	CroissantLLM Base	1.3B	INT4 Q8 FP16	175 tok/s 151 tok/s 112 tok/s	~139 ms ~139 ms ~142 ms
-	Phi-1	1.3B	INT4 Q8 FP16	175 tok/s 151 tok/s 112 tok/s	~139 ms ~139 ms ~142 ms
-	Phi-1.5	1.3B	INT4 Q8 FP16	175 tok/s 151 tok/s 112 tok/s	~139 ms ~139 ms ~142 ms
-	Mellum 2.1 12B A2.5B Thinking	12B (2.5B active)	INT4	172 tok/s	~285 ms
-	DeepSeek-R1 3B	3B	INT4 Q8 FP16	171 tok/s 122 tok/s 74 tok/s	~292 ms ~294 ms ~299 ms
-	Falcon3-3B	3B	INT4 Q8 FP16	169 tok/s 121 tok/s 74 tok/s	~292 ms ~294 ms ~299 ms
-	LFM2-VL 3B	3B	INT4 Q8 FP16	169 tok/s 121 tok/s 74 tok/s	~292 ms ~294 ms ~299 ms
-	Liquid D1 3B	3B	INT4 Q8 FP16	169 tok/s 121 tok/s 74 tok/s	~292 ms ~294 ms ~299 ms
-	Liquid D1-VL 3B	3B	INT4 Q8 FP16	169 tok/s 121 tok/s 74 tok/s	~292 ms ~294 ms ~299 ms
-	Liquid LFM2-VL 3B D1	3B	INT4 Q8 FP16	169 tok/s 121 tok/s 74 tok/s	~292 ms ~294 ms ~299 ms
-	Qwen2.5-3B	3B	INT4 Q8 FP16	169 tok/s 121 tok/s 74 tok/s	~292 ms ~294 ms ~299 ms
-	FrogNano 4B	4B	INT4 Q8 FP16	145 tok/s 99 tok/s 59 tok/s	~380 ms ~383 ms ~390 ms
-	Spark X2.5 4B	4B	INT4 Q8 FP16	145 tok/s 99 tok/s 59 tok/s	~380 ms ~383 ms ~390 ms
-	EmbeddingGemma 2	2B	INT4 Q8 FP16	140 tok/s 117 tok/s 83 tok/s	~207 ms ~208 ms ~212 ms
-	Phi-2	2.7B	INT4 Q8 FP16	125 tok/s 101 tok/s 68 tok/s	~268 ms ~270 ms ~275 ms
-	MaLLaM-3B	3B	INT4 Q8 FP16	120 tok/s 95 tok/s 63 tok/s	~294 ms ~296 ms ~302 ms
-	SmolLM3 3B	3B	INT4 Q8 FP16	120 tok/s 95 tok/s 63 tok/s	~294 ms ~296 ms ~302 ms
-	Falcon-7B	7B	INT4 Q8	105 tok/s 66 tok/s	~643 ms ~649 ms
-	Falcon3-7B	7B	INT4 Q8	101 tok/s 65 tok/s	~643 ms ~649 ms
-	Hy-MT2 7B	7B	INT4 Q8	101 tok/s 65 tok/s	~643 ms ~649 ms
-	Mistral-7B-v0.1	7.3B	INT4 Q8	98 tok/s 63 tok/s	~669 ms ~675 ms
-	Youtu Parsing Omni	8B	INT4 Q8	94 tok/s 59 tok/s	~731 ms ~737 ms
-	LensVLM 9B	9B	INT4 Q8	84 tok/s 50 tok/s	~820 ms ~898 ms
-	MiMo V2.6 Distill Qwen 9B	9B	INT4 Q8	84 tok/s 50 tok/s	~820 ms ~898 ms
-	ChatGLM3-6B-32K	6B	INT4 Q8	82 tok/s 60 tok/s	~559 ms ~563 ms
-	Yi-6B	6B	INT4 Q8	82 tok/s 60 tok/s	~559 ms ~563 ms
-	Falcon3-10B	10B	INT4 Q8	78 tok/s 43 tok/s	~908 ms ~1.1s
-	Falcon2-11B	11B	INT4 Q8	75 tok/s 41 tok/s	~996 ms ~1.2s
-	Hunyuan Lite	7B	INT4 Q8	74 tok/s 51 tok/s	~647 ms ~707 ms
-	OLMo 3 7B Base	7B	INT4 Q8	74 tok/s 51 tok/s	~647 ms ~707 ms
-	SEA-LION-7B	7.1B	INT4 Q8	74 tok/s 50 tok/s	~656 ms ~717 ms
-	SEA-LION-7B-Instruct	7.1B	INT4 Q8	74 tok/s 50 tok/s	~656 ms ~717 ms
-	Sahabat-AI-Llama3-8B-Instruct	8B	INT4 Q8	68 tok/s 43 tok/s	~735 ms ~869 ms
-	Typhoon-2-8B	8B	INT4 Q8	68 tok/s 43 tok/s	~735 ms ~869 ms
-	GLM-4-9B	9B	INT4	62 tok/s	~825 ms
-	GLM-4-9B-Chat	9B	INT4	62 tok/s	~825 ms
-	GLM-4-9B-Chat-1M	9B	INT4	62 tok/s	~825 ms
-	Yi-9B	9B	INT4	62 tok/s	~825 ms
-	Sahabat-AI-Gemma2-9B	9.2B	INT4	61 tok/s	~842 ms
-	Sahabat-AI-Gemma2-9B-Instruct	9.2B	INT4	61 tok/s	~842 ms
-	GreenMind-14B-R1	14B	INT4	40 tok/s	~1.5s

NVIDIA RTX 5070 (12GB)

VRAM Scaling by Context Length

Best Models to Run on NVIDIA RTX 5070 (12GB)

Inference Capacity

Fine-Tuning Capacity

Workload Recommendations

Frequently Asked Questions