What are the best models to run on NVIDIA RTX 4060 (8GB)?

Based on model rankings and 8 GB usable VRAM: Top Overall: Qwen3.5-9B (INT4) ~39 tok/s. Top Coding: K2 Horizon 7B (INT4) ~49 tok/s. Optimal Daily Driver: Granite 4.2 8B (INT4) ~44 tok/s. Maximum Model Size: Mellum 2.1 12B A2.5B Thinking (INT4) ~86 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 4060 (8GB)

Rank	Model	Parameters	Precision	TPS (Approx.)	TTFT
#121	Qwen3.5-9B	9B	INT4	39 tok/s	~1.7s
#127	K2 Horizon 7B	7B	INT4	49 tok/s	~1.3s
#136	Qwen3.5-4B	4B	INT4 Q8	77 tok/s 48 tok/s	~768 ms ~776 ms
#145	NVIDIA Nemotron 3 Nano 30B-A3B	3.5B (30B active)	INT4 Q8	12 tok/s 7 tok/s	~5.3s ~5.8s
#152	Granite 4.2 8B	8B	INT4	44 tok/s	~1.5s
#157	Gemma 4 E4B	8B	INT4	44 tok/s	~1.5s
#180	Gemma 3 12B	12B	INT4	27 tok/s	~2.6s
#185	Ministral 3 8B	8B	INT4	28 tok/s	~1.8s
#187	OLMo 3 7B Think	7B	INT4	32 tok/s	~1.4s
#188	Qwen3.5-2B	2B	INT4 Q8 FP16	122 tok/s 83 tok/s 48 tok/s	~410 ms ~414 ms ~423 ms
#189	MiniCPM5-2B	2B	INT4 Q8 FP16	122 tok/s 83 tok/s 48 tok/s	~410 ms ~414 ms ~423 ms
#193	Gemma 4 E2B	5.1B	INT4 Q8	63 tok/s 37 tok/s	~965 ms ~1.1s
#195	Ministral 3 3B	3B	INT4 Q8	60 tok/s 45 tok/s	~594 ms ~600 ms
#196	DeepSeek-R1 8B	8B	INT4	45 tok/s	~1.5s
#198	Gemma 2 9B	9B	INT4	39 tok/s	~1.7s
#201	Qwen3-4B	4B	INT4 Q8	77 tok/s 48 tok/s	~768 ms ~776 ms
#203	Gemma 3 4B	4B	INT4 Q8	77 tok/s 48 tok/s	~768 ms ~776 ms
#204	DeepSeek-R1 7B	7B	INT4 Q8	50 tok/s 27 tok/s	~1.3s ~1.5s
#206	Qwen3.5-0.8B	0.8B	INT4 Q8 FP16	203 tok/s 155 tok/s 101 tok/s	~170 ms ~172 ms ~175 ms
#207	Llama 3.1 8B	8B	INT4	44 tok/s	~1.5s
#207	Qwen3-8B	8B	INT4	44 tok/s	~1.5s
#212	Llama 3 8B	8B	INT4	44 tok/s	~1.5s
#213	Qwen3-1.7B	1.7B	INT4 Q8 FP16	135 tok/s 94 tok/s 55 tok/s	~352 ms ~355 ms ~362 ms
#214	Gemma 3 270M	0.27B	INT4 Q8 FP16	251 tok/s 224 tok/s 178 tok/s	~61 ms ~61 ms ~62 ms
#216	Qwen3-0.6B	0.6B	INT4 Q8 FP16	231 tok/s 182 tok/s 124 tok/s	~127 ms ~128 ms ~131 ms
#217	Phi-4-Mini	3.8B	INT4 Q8	79 tok/s 50 tok/s	~732 ms ~739 ms
#218	Qwen2.5-7B	7B	INT4	49 tok/s	~1.3s
#220	Ministral-8B-2410	8B	INT4	44 tok/s	~1.5s
#221	DeepSeek-R1 1.5B	1.5B	INT4 Q8 FP16	146 tok/s 102 tok/s 62 tok/s	~312 ms ~315 ms ~321 ms
#222	Llama 3.2 3B	3B	INT4 Q8 FP16	94 tok/s 61 tok/s 32 tok/s	~588 ms ~594 ms ~658 ms
#223	Phi-3-mini	3.8B	INT4 Q8	79 tok/s 50 tok/s	~732 ms ~739 ms
#224	Gemma 3n E2B IT	6B (2B active)	INT4	57 tok/s	~483 ms
#225	Gemma 2 2B	2B	INT4 Q8 FP16	122 tok/s 83 tok/s 48 tok/s	~410 ms ~414 ms ~423 ms
#226	Mistral-7B-Instruct-v0.1	7.3B	INT4	47 tok/s	~1.4s
#227	Llama 3.2 1B	1B	INT4 Q8 FP16	181 tok/s 134 tok/s 85 tok/s	~215 ms ~217 ms ~221 ms
#230	OLMo 3 7B Instruct	7B	INT4	32 tok/s	~1.4s
#231	Qwen2-7B	7B	INT4	49 tok/s	~1.3s
#232	Phi-3-small	7B	INT4	49 tok/s	~1.3s
#233	Mistral-7B-Instruct-v0.2	7.3B	INT4	47 tok/s	~1.4s
#234	Gemma 3 1B	1B	INT4 Q8 FP16	181 tok/s 134 tok/s 85 tok/s	~215 ms ~217 ms ~221 ms
#236	Gemma 1 7B	7B	INT4	32 tok/s	~1.4s
#237	Gemma 1 2B	2B	INT4 Q8 FP16	132 tok/s 87 tok/s 50 tok/s	~410 ms ~413 ms ~422 ms
#238	ChatGLM3-6B	6B	INT4	36 tok/s	~1.2s
#239	ChatGLM2-6B	6B	INT4	36 tok/s	~1.2s
#240	ChatGLM-6B	6B	INT4	36 tok/s	~1.2s
Unranked Models (Sorted by Speed)
-	DINOv3 ViT-L/16	0.3B	INT4 Q8 FP16	286 tok/s 245 tok/s 186 tok/s	~66 ms ~67 ms ~68 ms
-	Qwen2-0.5B	0.5B	INT4 Q8 FP16	247 tok/s 199 tok/s 139 tok/s	~106 ms ~107 ms ~110 ms
-	Qwen2.5-0.5B	0.5B	INT4 Q8 FP16	247 tok/s 199 tok/s 139 tok/s	~106 ms ~107 ms ~110 ms
-	ERNIE-4.5-0.3B	0.3B	INT4 Q8 FP16	241 tok/s 213 tok/s 167 tok/s	~67 ms ~67 ms ~69 ms
-	ERNIE-4.5-0.3B-Base	0.3B	INT4 Q8 FP16	241 tok/s 213 tok/s 167 tok/s	~67 ms ~67 ms ~69 ms
-	Liquid D1-Omni 600M	0.6B	INT4 Q8 FP16	231 tok/s 182 tok/s 124 tok/s	~127 ms ~128 ms ~131 ms
-	Falcon-1B	1B	INT4 Q8 FP16	194 tok/s 140 tok/s 87 tok/s	~214 ms ~216 ms ~221 ms
-	Falcon3-1B	1B	INT4 Q8 FP16	181 tok/s 134 tok/s 85 tok/s	~215 ms ~217 ms ~221 ms
-	MiniCPM-V 4.7 1B	1B	INT4 Q8 FP16	181 tok/s 134 tok/s 85 tok/s	~215 ms ~217 ms ~221 ms
-	Qwen2-1.5B	1.5B	INT4 Q8 FP16	146 tok/s 102 tok/s 62 tok/s	~312 ms ~315 ms ~321 ms
-	Qwen2.5-1.5B	1.5B	INT4 Q8 FP16	146 tok/s 102 tok/s 62 tok/s	~312 ms ~315 ms ~321 ms
-	Spark X2.5 1.7B	1.7B	INT4 Q8 FP16	135 tok/s 94 tok/s 55 tok/s	~352 ms ~355 ms ~362 ms
-	Hy-MT2 1.8B	1.8B	INT4 Q8 FP16	131 tok/s 90 tok/s 53 tok/s	~370 ms ~373 ms ~381 ms
-	Falcon-3B	3B	INT4 Q8 FP16	100 tok/s 63 tok/s 33 tok/s	~588 ms ~594 ms ~658 ms
-	CroissantLLM Base	1.3B	INT4 Q8 FP16	98 tok/s 81 tok/s 56 tok/s	~276 ms ~278 ms ~284 ms
-	Phi-1	1.3B	INT4 Q8 FP16	98 tok/s 81 tok/s 56 tok/s	~276 ms ~278 ms ~284 ms
-	Phi-1.5	1.3B	INT4 Q8 FP16	98 tok/s 81 tok/s 56 tok/s	~276 ms ~278 ms ~284 ms
-	DeepSeek-R1 3B	3B	INT4 Q8 FP16	96 tok/s 61 tok/s 32 tok/s	~588 ms ~594 ms ~658 ms
-	Falcon3-3B	3B	INT4 Q8 FP16	94 tok/s 61 tok/s 32 tok/s	~588 ms ~594 ms ~658 ms
-	LFM2-VL 3B	3B	INT4 Q8 FP16	94 tok/s 61 tok/s 32 tok/s	~588 ms ~594 ms ~658 ms
-	Liquid D1 3B	3B	INT4 Q8 FP16	94 tok/s 61 tok/s 32 tok/s	~588 ms ~594 ms ~658 ms
-	Liquid D1-VL 3B	3B	INT4 Q8 FP16	94 tok/s 61 tok/s 32 tok/s	~588 ms ~594 ms ~658 ms
-	Liquid LFM2-VL 3B D1	3B	INT4 Q8 FP16	94 tok/s 61 tok/s 32 tok/s	~588 ms ~594 ms ~658 ms
-	Qwen2.5-3B	3B	INT4 Q8 FP16	94 tok/s 61 tok/s 32 tok/s	~588 ms ~594 ms ~658 ms
-	Mellum 2.1 12B A2.5B Thinking	12B (2.5B active)	INT4	86 tok/s	~674 ms
-	FrogNano 4B	4B	INT4 Q8	77 tok/s 48 tok/s	~768 ms ~776 ms
-	Spark X2.5 4B	4B	INT4 Q8	77 tok/s 48 tok/s	~768 ms ~776 ms
-	EmbeddingGemma 2	2B	INT4 Q8 FP16	73 tok/s 58 tok/s 37 tok/s	~416 ms ~419 ms ~464 ms
-	Phi-2	2.7B	INT4 Q8 FP16	63 tok/s 49 tok/s 28 tok/s	~541 ms ~546 ms ~652 ms
-	MaLLaM-3B	3B	INT4 Q8	60 tok/s 45 tok/s	~594 ms ~600 ms
-	SmolLM3 3B	3B	INT4 Q8	60 tok/s 45 tok/s	~594 ms ~600 ms
-	Falcon-7B	7B	INT4 Q8	51 tok/s 27 tok/s	~1.3s ~1.5s
-	Falcon3-7B	7B	INT4	49 tok/s	~1.3s
-	Hy-MT2 7B	7B	INT4	49 tok/s	~1.3s
-	Mistral-7B-v0.1	7.3B	INT4	47 tok/s	~1.4s
-	Youtu Parsing Omni	8B	INT4	45 tok/s	~1.5s
-	LensVLM 9B	9B	INT4	39 tok/s	~1.7s
-	MiMo V2.6 Distill Qwen 9B	9B	INT4	39 tok/s	~1.7s
-	ChatGLM3-6B-32K	6B	INT4	36 tok/s	~1.2s
-	Yi-6B	6B	INT4	36 tok/s	~1.2s
-	Falcon3-10B	10B	INT4	34 tok/s	~2.0s
-	Falcon2-11B	11B	INT4	33 tok/s	~2.2s
-	Hunyuan Lite	7B	INT4	32 tok/s	~1.4s
-	OLMo 3 7B Base	7B	INT4	32 tok/s	~1.4s
-	SEA-LION-7B	7.1B	INT4	32 tok/s	~1.4s
-	SEA-LION-7B-Instruct	7.1B	INT4	32 tok/s	~1.4s
-	Sahabat-AI-Llama3-8B-Instruct	8B	INT4	28 tok/s	~1.8s
-	Typhoon-2-8B	8B	INT4	28 tok/s	~1.8s

NVIDIA RTX 4060 (8GB)

VRAM Scaling by Context Length

Best Models to Run on NVIDIA RTX 4060 (8GB)

Inference Capacity

Fine-Tuning Capacity

Workload Recommendations

Frequently Asked Questions