▣~/runthismodel▍
daemon okbuild 5a3c91d00:00:00Z

NVIDIA GeForce RTX 3070 vs NVIDIA GeForce RTX 3090 Ti

Head-to-head AI inference comparison across 145 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 3070
  • 8GB
  • ampere
  • nvidia
  • $499
  • 132 of 145
  • 0 models
NVIDIA GeForce RTX 3090 Ti
  • 24GB
  • ampere
  • nvidia
  • $1,999
  • 142 of 145
  • 44 models

Where NVIDIA GeForce RTX 3070 pulls ahead

  • No standout wins.

Where NVIDIA GeForce RTX 3090 Ti pulls ahead

Language Models74 models

F
—
Qwen 2.5 32B
32B · Alibaba
22
A
F
—
Skyfall 31B v4.2
31B · TheDrummer
22
A
F
—
Qwen3 30B-A3B
30.5B · Alibaba
22
A
D
—
Gemma 3 27B
27B · Google
22
S
D
—
Dolphin Mistral 24B (Venice Edition)
24B · Cognitive Computations
22
S
D
—
Dolphin 3.0 R1 Mistral 24B
24B · Cognitive Computations
22
S
D
—
Cydonia 24B v4.3
24B · TheDrummer
22
S
D
—
Mistral Small 22B
22B · Mistral AI
22
S
D
—
Magnum v4 22B
22B · Anthracite
22
S
D
—
DeepSeek MoE 16B
16.4B · DeepSeek
42
S
C
—
Rocinante XL 16B v1
16B · TheDrummer
42
S
C
—
Phi-4
14B · Microsoft
42
S
C
—
Qwen 2.5 14B
14B · Alibaba
42
S
F
—
Mixtral 8x7B Instruct
46.7B · Mistral AI
17
C
F
—
Phi-3.5 MoE
41.9B · Microsoft
18
C
B
—
Gemma 3 12B
12B · Google
42
S
B
—
Mistral Nemo 12B
12B · Mistral AI
42
S
B
—
Magnum v4 12B
12B · Anthracite
42
S
B
—
Rocinante 12B v1.1
12B · TheDrummer
42
S
B
—
Mistral Nemo Base 12B
12B · Mistral AI
42
S
B
32
Gemma 3 MoE 9B
9B · Google
60
S
F
—
Magnum v4 72B
72B · Anthracite
—
D
F
—
Llama 3.1 70B Instruct
70B · Meta
—
D
F
—
Euryale L3.3 70B v2.3
70B · Sao10K
—
D
F
—
Llama 3.1 70B (lorablated)
70B · mlabonne
—
D
A
—
Solar 10.7B
10.7B · Upstage
42
S
A
34
Falcon 3 10B
10B · TII
60
S
A
34
Gemma 2 9B Instruct
9.2B · Google
60
S
A
34
Yi 1.5 9B Chat
9B · 01.AI
60
S
F
—
Qwen3 235B-A22B
235B · Alibaba
—
F
F
—
Mixtral 8x22B Instruct
141B · Mistral AI
—
F
S
34
DeepSeek R1 Distill 8B
8B · DeepSeek
60
S
S
34
Llama 3.1 8B Instruct
8B · Meta
60
S
S
34
Granite 3.3 8B
8B · IBM
60
S
S
34
Dolphin 3.0 Llama 3.1 8B
8B · Cognitive Computations
60
S
S
34
NeuralDaredevil 8B (abliterated)
8B · mlabonne
60
S
S
34
Llama 3.1 8B Instruct (abliterated)
8B · mlabonne
60
S
S
34
Stheno L3 8B v3.2
8B · Sao10K
60
S
S
34
Qwen3 8B Base
8B · Alibaba
60
S
S
34
EXAONE 3.5 7.8B
7.8B · LG AI
60
S
S
34
InternLM 2.5 7B
7.7B · Shanghai AI Lab
60
S
S
34
Qwen 2.5 7B Instruct
7.6B · Alibaba
60
S
S
34
Mistral 7B Instruct v0.3
7.3B · Mistral AI
60
S
S
34
Falcon 3 7B
7B · TII
60
S
S
34
OLMo 2 7B
7B · Allen AI
60
S
S
34
OpenChat 3.5 7B
7B · OpenChat
60
S
S
34
OLMoE 1B-7B
6.9B · AI2
60
S
S
34
Yi 1.5 6B Chat
6B · 01.AI
60
S
S
60
Gemma 3 4B
4B · Google
96
S
S
60
Nemotron Mini 4B
4B · NVIDIA
96
S
S
60
Danube 3 4B
4B · H2O.ai
96
S
S
60
Phi-3.5 Mini 3.8B
3.8B · Microsoft
96
S
S
60
Phi-4 Mini 3.8B
3.8B · Microsoft
96
S
S
60
Granite 3.0 3B-A800M
3.4B · IBM
96
S
S
60
Llama 3.2 3B Instruct
3.2B · Meta
96
S
S
60
Qwen 2.5 3B
3B · Alibaba
96
S
S
60
Falcon 3 3B
3B · TII
96
S
S
60
StableLM Zephyr 3B
3B · Stability AI
96
S
S
60
Rocket 3B
3B · Pansophic
96
S
S
60
Gemma 2 2B
2.6B · Google
96
S
S
60
EXAONE 3.5 2.4B
2.4B · LG AI
96
S
S
90
Granite 3.3 2B
2B · IBM
132
S
S
90
SmolLM2 1.7B
1.7B · HuggingFace
132
S
S
90
Qwen 2.5 1.5B
1.5B · Alibaba
132
S
S
90
DeepSeek R1 Distill 1.5B
1.5B · DeepSeek
132
S
S
90
Granite 3.0 1B-A400M
1.3B · IBM
132
S
S
90
Llama 3.2 1B Instruct
1.24B · Meta
132
S
S
90
TinyLlama 1.1B
1.1B · TinyLlama
132
S
S
90
Gemma 3 1B
1B · Google
132
S
S
90
Falcon 3 1B
1B · TII
132
S
S
90
Qwen 2.5 0.5B
0.5B · Alibaba
132
S
S
90
Danube 3 500M
0.5B · H2O.ai
132
S
S
90
SmolLM2 360M
0.36B · HuggingFace
132
S
S
90
SmolLM2 135M
0.135B · HuggingFace
132
S

Code Models17 models

D
—
Codestral 22B (abliterated)
22B · failspy
22
S
C
—
Qwen 2.5 Coder 14B
14B · Alibaba
42
S
B
—
Code Llama 13B Instruct
13B · Meta
42
S
A
34
Yi Coder 9B
9B · 01.AI
60
S
A
34
CodeGemma 7B
8.5B · Google
60
S
S
34
Qwen 2.5 Coder 7B
7.6B · Alibaba
60
S
S
34
StarCoder2 7B
7B · BigCode
60
S
S
34
Code Llama 7B
7B · Meta
60
S
S
34
DeepSeek Coder 6.7B
6.7B · DeepSeek
60
S
S
60
Qwen 2.5 Coder 3B
3B · Alibaba
96
S
S
60
StarCoder2 3B
3B · BigCode
96
S
S
60
Stable Code 3B
3B · Stability AI
96
S
S
90
CodeGemma 2B
2B · Google
132
S
S
90
Qwen 2.5 Coder 1.5B
1.5B · Alibaba
132
S
S
90
Yi Coder 1.5B
1.5B · 01.AI
132
S
S
90
DeepSeek Coder 1.3B
1.3B · DeepSeek
132
S
S
90
Qwen 2.5 Coder 0.5B
0.5B · Alibaba
132
S

Multimodal & Vision6 models

S
34
LLaVA 1.6 7B
7B · LLaVA
60
S
S
60
Phi-3.5 Vision
4.2B · Microsoft
96
S
S
60
PaliGemma 3B
3B · Google
96
S
S
60
Qwen2-VL 2B
2.2B · Alibaba
96
S
S
90
MiniCPM-V 2.6
2B · OpenBMB
132
S
S
90
Moondream 2
1.8B · Moondream
132
S

Image Generation9 models

D
—
FLUX.1 Schnell (GGUF)
12B · Black Forest Labs
42
S
D
—
FLUX.1 Dev (GGUF)
12B · Black Forest Labs
42
S
C
44
Stable Diffusion 3 Medium (GGUF)
2.5B · Stability AI
96
S
S
60
Stable Diffusion XL (CoreML)
3.5B · Stability AI
96
S
S
60
SDXL Turbo (GGUF)
3.5B · Stability AI
96
S
S
90
Stable Diffusion 2.1 Base (CoreML)
0.86B · Stability AI / Apple
132
S
S
90
Stable Diffusion 1.5 (CoreML)
0.86B · Runway
132
S
S
90
Stable Diffusion 1.5 (GGUF)
0.86B · Runway / GPUStack
132
S
S
90
Stable Diffusion 2.1 (GGUF)
0.86B · Stability AI
132
S

Speech9 models

S
90
Whisper Large v3
1.55B · OpenAI
132
S
S
90
Whisper Large v3 Turbo
0.81B · OpenAI
132
S
S
90
Whisper Medium
0.77B · OpenAI
132
S
S
90
Distil-Whisper Large v3
0.76B · HuggingFace
132
S
S
90
Whisper Small
0.24B · OpenAI
132
S
S
90
Whisper Base
0.074B · OpenAI
132
S
S
90
Whisper Base English
0.074B · OpenAI
132
S
S
90
Whisper Tiny English (Quantized)
0.039B · OpenAI
132
S
S
90
Whisper Tiny
0.039B · OpenAI
132
S

Text-to-Speech14 models

S
90
Kokoro 82M TTS
0.082B · Kokoro
132
S
S
90
Piper TTS - Amy (English)
0.02B · Rhasspy
132
S
S
90
Piper TTS - Lessac (English)
0.02B · Rhasspy
132
S
S
90
Piper TTS - LibriTTS-R (English)
0.02B · Rhasspy
132
S
S
90
Piper TTS - Spanish (MLS)
0.02B · Rhasspy
132
S
S
90
Piper TTS - French (Siwis)
0.02B · Rhasspy
132
S
S
90
Piper TTS - German (Thorsten)
0.02B · Rhasspy
132
S
S
90
Piper TTS - Chinese (Huayan)
0.02B · Rhasspy
132
S
S
90
Piper TTS - Japanese (Kokoro)
0.02B · Rhasspy
132
S
S
90
Piper TTS - Korean
0.02B · Rhasspy
132
S
S
90
Piper TTS - Russian (Irina)
0.02B · Rhasspy
132
S
S
90
Piper TTS - Portuguese (Faber)
0.02B · Rhasspy
132
S
S
90
Piper TTS - Italian (Riccardo)
0.02B · Rhasspy
132
S
S
90
Piper TTS - Arabic (Kareem)
0.02B · Rhasspy
132
S

Embeddings5 models

S
90
BGE Large EN v1.5
0.335B · BAAI
132
S
S
90
Nomic Embed Text v1.5
0.137B · Nomic AI
132
S
S
90
BGE Small EN v1.5
0.033B · BAAI
132
S
S
90
Snowflake Arctic Embed S
0.033B · Snowflake
132
S
S
90
all-MiniLM-L6-v2
0.023B · Sentence Transformers
132
S

Rerankers2 models

S
90
BGE Reranker v2 M3
0.568B · BAAI
132
S
S
90
Jina Reranker Tiny EN
0.033B · Jina AI
132
S
© runthismodel · 2026privacytermsdisclaimerchangelogembed badgerunpodvast.aihuggingfaceollamalm-studiomade for the people who actually read GGUF metadata
 ┌─┐                ╔══╗     ╔══╗
 │░│  RUN  THIS  M  ║▓▓║ DEL ║▓▓║
 └─┘                ╚══╝     ╚══╝