NVIDIA GeForce RTX 4070 Ti Super
16 GB GDDR6X · 672 GB/s
From
$779
Estimated street price
VRAM
16 GB
Bandwidth
672 GB/s
TDP
285W
Models
26
Tier
Capable
The NVIDIA GeForce RTX 4070 Ti Super with 16 GB GDDR6X VRAM can handle 26 AI models across reasoning, coding, chat. Best performance: Gemma 4 26B-A4B at 229 tok/s (excellent). For AI coding workflows, it supports the Capable AI Coding tier, handling single model workflows well. Current price: approximately $779.
Source: OwnRig methodology
16 GB
672 GB/s
GDDR6X
285W
2-slot, 300mm
Builder Capability: Capable AI Coding
Runs 16-22B coding models comfortably, or 32B at reduced quality. Handles single model workflows well.
Inference Backends
The software stacks that matter most for real-world inference on this device.
CUDA
productionPrimary high-performance backend for NVIDIA inference workloads.
Vulkan
stableFallback backend for llama.cpp and related local runtimes.
What it can run
26 models| Arcee Trinity Mini 26B | Q3_K_M | 64 tok/s | Excellent |
| Arcee Trinity Nano 6B | Q8_0 | 119 tok/s | Excellent |
| DeepSeek R1 Distill Qwen 32B | Q3_K_M | 15 tok/s | Acceptable |
| DeepSeek V3 | Q2_K | – | Not viable |
| Gemma 3 27B | Q3_K_M | 12 tok/s | Acceptable |
| Gemma 4 26B-A4B | Q3_K_M | 229 tok/s | Excellent |
| Gemma 4 31B | Q3_K_M | 15 tok/s | Acceptable |
| Gemma 4 E2B | Q8_0 | 101 tok/s | Excellent |
| Gemma 4 E4B | Q8_0 | 62 tok/s | Excellent |
| GigaChat Lightning 10B | Q8_0 | 72 tok/s | Acceptable |
| Llama 3.1 8B Instruct | Q8_0 | 75 tok/s | Excellent |
| Llama 3.2 11B Vision | Q8_0 | 55 tok/s | Excellent |
| Llama 3.2 1B Instruct | Q8_0 | 190 tok/s | Excellent |
| Llama 3.2 3B Instruct | Q8_0 | 130 tok/s | Excellent |
| Mistral Small 24B Instruct | Q3_K_M | 18 tok/s | Acceptable |
| NVIDIA Nemotron-3-super-120B-A12B | Q2_K | – | Not viable |
| Phi-4 14B | Q5_K_M | 42 tok/s | Good |
| Phi-4 Mini | Q8_0 | 120 tok/s | Excellent |
| Qwen 2.5 Coder 32B Instruct | Q3_K_M | 16 tok/s | Acceptable |
| Qwen3-14B Instruct | Q8_0 | 29 tok/s | Good |
| Qwen3.5-122B-A10B | Q3_K_M | – | Not viable |
| Qwen3.5-27B | Q3_K_M | 32 tok/s | Acceptable |
| Qwen3.5-397B (MoE) | Q2_K | – | Not viable |
| Qwen3.6-27B | Q3_K_M | 32 tok/s | Acceptable |
| Stable Diffusion 3.5 Large | FP16 | – | Excellent |
| Whisper Large V3 Turbo | FP16 | – | Excellent |
Showing 26 of 26 entries
Buy Used
Prices and availability vary. Inspect hardware before purchasing. Some links may be affiliate links.
Frequently Asked Questions
- What AI models can NVIDIA GeForce RTX 4070 Ti Super run?
- The NVIDIA GeForce RTX 4070 Ti Super can run 26 AI models. Top performers include Gemma 4 26B-A4B, Llama 3.2 1B Instruct, Llama 3.2 3B Instruct. See the full compatibility table above for speeds and quality ratings.
- Is NVIDIA GeForce RTX 4070 Ti Super good for AI coding?
- Yes. With 16 GB, the NVIDIA GeForce RTX 4070 Ti Super handles single-model coding workflows well at the Capable tier.
- How much VRAM does NVIDIA GeForce RTX 4070 Ti Super have?
- The NVIDIA GeForce RTX 4070 Ti Super has 16 GB of GDDR6X VRAM with 672 GB/s bandwidth.
- Can NVIDIA GeForce RTX 4070 Ti Super run 70B models?
- 70B models can run on the NVIDIA GeForce RTX 4070 Ti Super with CPU offloading, but performance will be reduced. Consider a GPU with 48GB+ VRAM for full-speed 70B inference.
- Is NVIDIA GeForce RTX 4070 Ti Super worth it for AI?
- At $779, the NVIDIA GeForce RTX 4070 Ti Super offers 16 GB VRAM and runs 26 AI models. It works for smaller models and experimentation.
Own this GPU?
See every AI model it supports, expected performance, and how to build around it.
Related Guides
Buying Guide
How to Choose Your First AI GPU
A data-backed buying guide to choosing the right GPU for running AI models locally. VRAM explained, budget tiers compared, and specific GPU recommendations with compatible models.
Tutorial
Running Gemma 4 locally: which GPU you actually need
Gemma 4 VRAM requirements for every variant: E2B, E4B, 26B-A4B, and 31B. Which GPUs can run each, what quantization to use, and the honest call on RTX 4060 vs RTX 4090.
Buying Guide
Best GPUs for Stable Diffusion, Flux, and SD3 in 2026
GPU requirements for SDXL, Stable Diffusion 3 Medium, SD 3.5 Large, and FLUX.1 Dev. Per-GPU performance verdicts for RTX 4060 Ti, RTX 4070, RTX 4090, and Apple Silicon.