GeForce RTX 4070 SUPER
NVIDIA · Consumer GPU · 2024
We earn a commission from qualifying purchases · Prices may vary
Price checked Aug 15, 2026
Performance Benchmarks
LLM Inference all sourced rows →
| Model | Metric | Value | Source |
|---|---|---|---|
|
Llama-3.1-8B
Q4_K_M Token generation: single user, batch 1, 4k context, mean of 3 runs |
tokens per second |
92
tok/s
llama.cpp b3500 (CUDA) · 2026-05-22
|
Unverified community MyAIHardware llama.cpp Benchmarks ↗ |
|
Llama-3.1-8B
Q4_K_M Prompt processing: 512-token prompt, batch 1, mean of 3 runs |
prompt tokens per second |
2,900
tok/s
llama.cpp b3500 (CUDA) · 2026-05-22
|
Unverified community MyAIHardware llama.cpp Benchmarks ↗ |
|
Qwen3-8B
Q4_K_XL Token generation: 16K context, batch 1, Ubuntu 24.04, on-hardware lab measurement |
tokens per second |
56.2
tok/s
llama.cpp llama-bench, CUDA 12.8 · 2025-12-09
|
Unverified community Hardware Corner LLM GPU Rankings ↗ |
Full Specifications
Related GPUs
Common Questions
Can the GeForce RTX 4070 SUPER run local LLMs?
Yes, if the model fits in its 12 GB of memory — VRAM capacity decides which models load at all, while its 504 GB/s of bandwidth decides how fast tokens generate. 8B-class models at Q4 quantization fit comfortably; larger 70B-class models need a card with more VRAM.
How much VRAM does the GeForce RTX 4070 SUPER have?
GeForce RTX 4070 SUPER has 12 GB of video memory with 504 GB/s of memory bandwidth and a 220 W TDP , per the specification values in our hardware database.
Is the GeForce RTX 4070 SUPER worth it for AI workloads?
At a $599 MSRP, its value depends on whether your models fit in 12 GB. Compare its VRAM and bandwidth against your target models with our VRAM calculator, or see how it stacks up in head-to-head comparisons.
Guides & Tools
CompareAIHardware.com participates in the Amazon Associates program. As an Amazon Associate, we earn from qualifying purchases.