NVIDIA GeForce GTX 1650 vs NVIDIA GeForce RTX 2080 Ti
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 GTX 1650
- 4GB
- turing
- nvidia
- $149
- 99 of 109
- 0 models
NVIDIA GeForce RTX 2080 Ti
- 11GB
- turing
- nvidia
- $1,199
- 108 of 109
- 43 models
Where NVIDIA GeForce GTX 1650 pulls ahead
- No standout wins.
Where NVIDIA GeForce RTX 2080 Ti pulls ahead
- Phi-3.5 Mini 3.8BAvsS
- Gemma 3 4BAvsS
- Gemma 3 27BFvsD
- Phi-4 Mini 3.8BAvsS
- Qwen 2.5 32BFvsD
Language Models47 models
1650
tok/s
Model
tok/s
Ti
F
—
Phi-4
14B · Microsoft
36
A
F
—
Qwen 2.5 14B
14B · Alibaba
36
A
D
—
Gemma 3 12B
12B · Google
36
S
D
—
Solar 10.7B
10.7B · Upstage
36
S
D
—
Falcon 3 10B
10B · TII
62
S
D
—
Gemma 2 9B Instruct
9.2B · Google
62
S
D
—
Yi 1.5 9B Chat
9B · 01.AI
62
S
D
—
DeepSeek R1 Distill 8B
8B · DeepSeek
62
S
D
—
Llama 3.1 8B Instruct
8B · Meta
62
S
D
—
Granite 3.3 8B
8B · IBM
62
S
D
—
Qwen 2.5 7B Instruct
7.6B · Alibaba
62
S
D
—
Mistral Nemo 12B
12B · Mistral AI
36
A
C
31
EXAONE 3.5 7.8B
7.8B · LG AI
62
S
C
31
InternLM 2.5 7B
7.7B · Shanghai AI Lab
62
S
C
33
Mistral 7B Instruct v0.3
7.3B · Mistral AI
62
S
C
30
Falcon 3 7B
7B · TII
62
S
C
33
OLMo 2 7B
7B · Allen AI
62
S
C
33
OpenChat 3.5 7B
7B · OpenChat
62
S
F
—
Mistral Small 22B
22B · Mistral AI
—
C
B
39
Yi 1.5 6B Chat
6B · 01.AI
62
S
F
—
Qwen 2.5 32B
32B · Alibaba
—
D
F
—
Gemma 3 27B
27B · Google
—
D
A
78
Gemma 3 4B
4B · Google
94
S
A
78
Nemotron Mini 4B
4B · NVIDIA
94
S
A
78
Danube 3 4B
4B · H2O.ai
94
S
A
78
Phi-3.5 Mini 3.8B
3.8B · Microsoft
94
S
A
78
Phi-4 Mini 3.8B
3.8B · Microsoft
94
S
F
—
Llama 3.1 70B Instruct
70B · Meta
—
F
S
78
Llama 3.2 3B Instruct
3.2B · Meta
94
S
S
78
Qwen 2.5 3B
3B · Alibaba
94
S
S
78
Falcon 3 3B
3B · TII
94
S
S
78
StableLM Zephyr 3B
3B · Stability AI
94
S
S
78
Rocket 3B
3B · Pansophic
94
S
S
78
Gemma 2 2B
2.6B · Google
94
S
S
78
EXAONE 3.5 2.4B
2.4B · LG AI
94
S
S
114
Granite 3.3 2B
2B · IBM
132
S
S
114
SmolLM2 1.7B
1.7B · HuggingFace
132
S
S
114
Qwen 2.5 1.5B
1.5B · Alibaba
132
S
S
114
DeepSeek R1 Distill 1.5B
1.5B · DeepSeek
132
S
S
114
Llama 3.2 1B Instruct
1.24B · Meta
132
S
S
114
TinyLlama 1.1B
1.1B · TinyLlama
132
S
S
114
Gemma 3 1B
1B · Google
132
S
S
114
Falcon 3 1B
1B · TII
132
S
S
114
Qwen 2.5 0.5B
0.5B · Alibaba
132
S
S
114
Danube 3 500M
0.5B · H2O.ai
132
S
S
114
SmolLM2 360M
0.36B · HuggingFace
132
S
S
114
SmolLM2 135M
0.135B · HuggingFace
132
S
Code Models16 models
1650
tok/s
Model
tok/s
Ti
F
—
Qwen 2.5 Coder 14B
14B · Alibaba
36
A
D
—
Yi Coder 9B
9B · 01.AI
62
S
D
—
CodeGemma 7B
8.5B · Google
62
S
D
—
Code Llama 13B Instruct
13B · Meta
36
A
C
31
Qwen 2.5 Coder 7B
7.6B · Alibaba
62
S
C
33
StarCoder2 7B
7B · BigCode
62
S
C
35
Code Llama 7B
7B · Meta
62
S
C
35
DeepSeek Coder 6.7B
6.7B · DeepSeek
62
S
S
78
Qwen 2.5 Coder 3B
3B · Alibaba
94
S
S
78
StarCoder2 3B
3B · BigCode
94
S
S
78
Stable Code 3B
3B · Stability AI
94
S
S
114
CodeGemma 2B
2B · Google
132
S
S
114
Qwen 2.5 Coder 1.5B
1.5B · Alibaba
132
S
S
114
Yi Coder 1.5B
1.5B · 01.AI
132
S
S
114
DeepSeek Coder 1.3B
1.3B · DeepSeek
132
S
S
114
Qwen 2.5 Coder 0.5B
0.5B · Alibaba
132
S
Multimodal & Vision6 models
1650
tok/s
Model
tok/s
Ti
Image Generation9 models
1650
tok/s
Model
tok/s
Ti
F
—
Stable Diffusion 3 Medium (GGUF)
2.5B · Stability AI
94
A
C
52
SDXL Turbo (GGUF)
3.5B · Stability AI
94
S
B
78
Stable Diffusion XL (CoreML)
3.5B · Stability AI
94
S
F
—
FLUX.1 Schnell (GGUF)
12B · Black Forest Labs
—
D
F
—
FLUX.1 Dev (GGUF)
12B · Black Forest Labs
—
D
S
114
Stable Diffusion 2.1 Base (CoreML)
0.86B · Stability AI / Apple
132
S
S
114
Stable Diffusion 1.5 (CoreML)
0.86B · Runway
132
S
S
114
Stable Diffusion 1.5 (GGUF)
0.86B · Runway / GPUStack
132
S
S
114
Stable Diffusion 2.1 (GGUF)
0.86B · Stability AI
132
S
Speech9 models
1650
tok/s
Model
tok/s
Ti
B
112
Whisper Large v3
1.55B · OpenAI
132
S
S
114
Whisper Large v3 Turbo
0.81B · OpenAI
132
S
S
114
Whisper Medium
0.77B · OpenAI
132
S
S
114
Distil-Whisper Large v3
0.76B · HuggingFace
132
S
S
114
Whisper Small
0.24B · OpenAI
132
S
S
114
Whisper Base
0.074B · OpenAI
132
S
S
114
Whisper Base English
0.074B · OpenAI
132
S
S
114
Whisper Tiny English (Quantized)
0.039B · OpenAI
132
S
S
114
Whisper Tiny
0.039B · OpenAI
132
S
Text-to-Speech14 models
1650
tok/s
Model
tok/s
Ti
S
114
Kokoro 82M TTS
0.082B · Kokoro
132
S
S
114
Piper TTS - Amy (English)
0.02B · Rhasspy
132
S
S
114
Piper TTS - Lessac (English)
0.02B · Rhasspy
132
S
S
114
Piper TTS - LibriTTS-R (English)
0.02B · Rhasspy
132
S
S
114
Piper TTS - Spanish (MLS)
0.02B · Rhasspy
132
S
S
114
Piper TTS - French (Siwis)
0.02B · Rhasspy
132
S
S
114
Piper TTS - German (Thorsten)
0.02B · Rhasspy
132
S
S
114
Piper TTS - Chinese (Huayan)
0.02B · Rhasspy
132
S
S
114
Piper TTS - Japanese (Kokoro)
0.02B · Rhasspy
132
S
S
114
Piper TTS - Korean
0.02B · Rhasspy
132
S
S
114
Piper TTS - Russian (Irina)
0.02B · Rhasspy
132
S
S
114
Piper TTS - Portuguese (Faber)
0.02B · Rhasspy
132
S
S
114
Piper TTS - Italian (Riccardo)
0.02B · Rhasspy
132
S
S
114
Piper TTS - Arabic (Kareem)
0.02B · Rhasspy
132
S
Embeddings5 models
1650
tok/s
Model
tok/s
Ti
Rerankers2 models
1650
tok/s
Model
tok/s
Ti