NVIDIA GeForce RTX 4060 vs NVIDIA GeForce RTX 5060

Head-to-head AI inference comparison across 109 popular models. Each model is graded against both cards using its highest-quality quantization that still fits in VRAM. Bigger grade and faster tokens-per-second wins.

Spec
  • VRAM
  • Architecture
  • Vendor
  • MSRP
  • Models running
  • Wins (grade)
NVIDIA GeForce RTX 4060
  • 8GB
  • ada lovelace
  • nvidia
  • $299
  • 107 of 109
  • 0 models
NVIDIA GeForce RTX 5060
  • 8GB
  • blackwell
  • nvidia
  • $299
  • 107 of 109
  • 0 models

Language Models47 models

F
—
Llama 3.1 70B Instruct
70B · Meta
—
F
F
—
Qwen 2.5 32B
32B · Alibaba
—
F
D
—
Gemma 3 27B
27B · Google
—
D
D
—
Mistral Small 22B
22B · Mistral AI
—
D
C
—
Phi-4
14B · Microsoft
—
C
C
—
Qwen 2.5 14B
14B · Alibaba
—
C
B
—
Gemma 3 12B
12B · Google
—
B
B
—
Mistral Nemo 12B
12B · Mistral AI
—
B
A
—
Solar 10.7B
10.7B · Upstage
—
A
A
40
Falcon 3 10B
10B · TII
46
A
A
40
Gemma 2 9B Instruct
9.2B · Google
46
A
A
40
Yi 1.5 9B Chat
9B · 01.AI
46
A
S
40
DeepSeek R1 Distill 8B
8B · DeepSeek
46
S
S
40
Llama 3.1 8B Instruct
8B · Meta
46
S
S
40
Granite 3.3 8B
8B · IBM
46
S
S
40
EXAONE 3.5 7.8B
7.8B · LG AI
46
S
S
40
InternLM 2.5 7B
7.7B · Shanghai AI Lab
46
S
S
40
Qwen 2.5 7B Instruct
7.6B · Alibaba
46
S
S
40
Mistral 7B Instruct v0.3
7.3B · Mistral AI
46
S
S
40
Falcon 3 7B
7B · TII
46
S
S
40
OLMo 2 7B
7B · Allen AI
46
S
S
40
OpenChat 3.5 7B
7B · OpenChat
46
S
S
40
Yi 1.5 6B Chat
6B · 01.AI
46
S
S
70
Gemma 3 4B
4B · Google
78
S
S
70
Nemotron Mini 4B
4B · NVIDIA
78
S
S
70
Danube 3 4B
4B · H2O.ai
78
S
S
70
Phi-3.5 Mini 3.8B
3.8B · Microsoft
78
S
S
70
Phi-4 Mini 3.8B
3.8B · Microsoft
78
S
S
70
Llama 3.2 3B Instruct
3.2B · Meta
78
S
S
70
Qwen 2.5 3B
3B · Alibaba
78
S
S
70
Falcon 3 3B
3B · TII
78
S
S
70
StableLM Zephyr 3B
3B · Stability AI
78
S
S
70
Rocket 3B
3B · Pansophic
78
S
S
70
Gemma 2 2B
2.6B · Google
78
S
S
70
EXAONE 3.5 2.4B
2.4B · LG AI
78
S
S
102
Granite 3.3 2B
2B · IBM
114
S
S
102
SmolLM2 1.7B
1.7B · HuggingFace
114
S
S
102
Qwen 2.5 1.5B
1.5B · Alibaba
114
S
S
102
DeepSeek R1 Distill 1.5B
1.5B · DeepSeek
114
S
S
102
Llama 3.2 1B Instruct
1.24B · Meta
114
S
S
102
TinyLlama 1.1B
1.1B · TinyLlama
114
S
S
102
Gemma 3 1B
1B · Google
114
S
S
102
Falcon 3 1B
1B · TII
114
S
S
102
Qwen 2.5 0.5B
0.5B · Alibaba
114
S
S
102
Danube 3 500M
0.5B · H2O.ai
114
S
S
102
SmolLM2 360M
0.36B · HuggingFace
114
S
S
102
SmolLM2 135M
0.135B · HuggingFace
114
S

Code Models16 models

C
—
Qwen 2.5 Coder 14B
14B · Alibaba
—
C
B
—
Code Llama 13B Instruct
13B · Meta
—
B
A
40
Yi Coder 9B
9B · 01.AI
46
A
A
40
CodeGemma 7B
8.5B · Google
46
A
S
40
Qwen 2.5 Coder 7B
7.6B · Alibaba
46
S
S
40
StarCoder2 7B
7B · BigCode
46
S
S
40
Code Llama 7B
7B · Meta
46
S
S
40
DeepSeek Coder 6.7B
6.7B · DeepSeek
46
S
S
70
Qwen 2.5 Coder 3B
3B · Alibaba
78
S
S
70
StarCoder2 3B
3B · BigCode
78
S
S
70
Stable Code 3B
3B · Stability AI
78
S
S
102
CodeGemma 2B
2B · Google
114
S
S
102
Qwen 2.5 Coder 1.5B
1.5B · Alibaba
114
S
S
102
Yi Coder 1.5B
1.5B · 01.AI
114
S
S
102
DeepSeek Coder 1.3B
1.3B · DeepSeek
114
S
S
102
Qwen 2.5 Coder 0.5B
0.5B · Alibaba
114
S

Multimodal & Vision6 models

S
40
LLaVA 1.6 7B
7B · LLaVA
46
S
S
70
Phi-3.5 Vision
4.2B · Microsoft
78
S
S
70
PaliGemma 3B
3B · Google
78
S
S
70
Qwen2-VL 2B
2.2B · Alibaba
78
S
S
102
MiniCPM-V 2.6
2B · OpenBMB
114
S
S
102
Moondream 2
1.8B · Moondream
114
S

Image Generation9 models

D
—
FLUX.1 Schnell (GGUF)
12B · Black Forest Labs
—
D
D
—
FLUX.1 Dev (GGUF)
12B · Black Forest Labs
—
D
S
70
Stable Diffusion XL (CoreML)
3.5B · Stability AI
78
S
S
70
SDXL Turbo (GGUF)
3.5B · Stability AI
78
S
C
51
Stable Diffusion 3 Medium (GGUF)
2.5B · Stability AI
57
C
S
102
Stable Diffusion 2.1 Base (CoreML)
0.86B · Stability AI / Apple
114
S
S
102
Stable Diffusion 1.5 (CoreML)
0.86B · Runway
114
S
S
102
Stable Diffusion 1.5 (GGUF)
0.86B · Runway / GPUStack
114
S
S
102
Stable Diffusion 2.1 (GGUF)
0.86B · Stability AI
114
S

Speech9 models

S
102
Whisper Large v3
1.55B · OpenAI
114
S
S
102
Whisper Large v3 Turbo
0.81B · OpenAI
114
S
S
102
Whisper Medium
0.77B · OpenAI
114
S
S
102
Distil-Whisper Large v3
0.76B · HuggingFace
114
S
S
102
Whisper Small
0.24B · OpenAI
114
S
S
102
Whisper Base
0.074B · OpenAI
114
S
S
102
Whisper Base English
0.074B · OpenAI
114
S
S
102
Whisper Tiny English (Quantized)
0.039B · OpenAI
114
S
S
102
Whisper Tiny
0.039B · OpenAI
114
S

Text-to-Speech14 models

S
102
Kokoro 82M TTS
0.082B · Kokoro
114
S
S
102
Piper TTS - Amy (English)
0.02B · Rhasspy
114
S
S
102
Piper TTS - Lessac (English)
0.02B · Rhasspy
114
S
S
102
Piper TTS - LibriTTS-R (English)
0.02B · Rhasspy
114
S
S
102
Piper TTS - Spanish (MLS)
0.02B · Rhasspy
114
S
S
102
Piper TTS - French (Siwis)
0.02B · Rhasspy
114
S
S
102
Piper TTS - German (Thorsten)
0.02B · Rhasspy
114
S
S
102
Piper TTS - Chinese (Huayan)
0.02B · Rhasspy
114
S
S
102
Piper TTS - Japanese (Kokoro)
0.02B · Rhasspy
114
S
S
102
Piper TTS - Korean
0.02B · Rhasspy
114
S
S
102
Piper TTS - Russian (Irina)
0.02B · Rhasspy
114
S
S
102
Piper TTS - Portuguese (Faber)
0.02B · Rhasspy
114
S
S
102
Piper TTS - Italian (Riccardo)
0.02B · Rhasspy
114
S
S
102
Piper TTS - Arabic (Kareem)
0.02B · Rhasspy
114
S

Embeddings5 models

S
102
BGE Large EN v1.5
0.335B · BAAI
114
S
S
102
Nomic Embed Text v1.5
0.137B · Nomic AI
114
S
S
102
BGE Small EN v1.5
0.033B · BAAI
114
S
S
102
Snowflake Arctic Embed S
0.033B · Snowflake
114
S
S
102
all-MiniLM-L6-v2
0.023B · Sentence Transformers
114
S

Rerankers2 models

S
102
BGE Reranker v2 M3
0.568B · BAAI
114
S
S
102
Jina Reranker Tiny EN
0.033B · Jina AI
114
S