GeForce RTX 4060, AI & Machine Learning Benchmarks & Specs

8GB · AI Score 1.9/100 · first-party measured on 12 AI workloads

1.9 AI Score ✓ Measured

Every number on this page is first-party: GeForce RTX 4060 was run on our pinned 12-workload AI suite on 2026-07-11, with under 0.5% run-to-run variance. On Llama 3.1 8B (Q4_K_M) GeForce RTX 4060 delivers about 52.4 tokens/sec. Llama 3.3 70B does not fit. It needs roughly 42GB and this card has 8GB. For image generation, SDXL runs at 1.39 it/s, while FLUX.1-dev won't fit at BF16 (needs ~26GB). 9 of the 12 workloads won't fit on 8GB at the tested precision, Qwen2.5-Coder 14B, Qwen3 32B, Llama 3.3 70B, Z-Image Turbo and others. We publish those as hard gates rather than quietly dropping to a smaller quant.

Bench notes: from the person who ran it

Short version: 8GB gated 9 of my 12 workloads. If AI is any part of why you're buying, don't buy 8GB, the model that doesn't fit doesn't run slow, it doesn't run. Quick note on the setup: all my AI benchmarking was done on rented cloud GPUs, I used all three of Vast.ai, RunPod and Modal depending on which had the card, and they all have their pros and cons. Same pinned harness on every run, and everything here got double-checked before it went up.

AI & Machine Learning benchmark results

Text Generation tok/s 5

WorkloadResultTelemetryData
Qwen3 4B86.38 tok/s
Q4_K_M
✓ Measured
Llama 3.1 8B52.4 tok/s
Q4_K_M
✓ Measured
Qwen2.5-Coder 14B✕ Won't fit needs ~11.5 GBVRAM-gated at this precision✓ Measured
Qwen3 32B✕ Won't fit needs ~23 GBVRAM-gated at this precision✓ Measured
Llama 3.3 70B✕ Won't fit needs ~46 GBVRAM-gated at this precision✓ Measured

Image Generation images/min 3

WorkloadResultTelemetryData
Stable Diffusion XL2.78 images/min
5.6 GB peak21.5 s/img
✓ Measured
Z-Image Turbo✕ Won't fit needs ~13 GBVRAM-gated at this precision✓ Measured
FLUX.1 dev✕ Won't fit needs ~26 GBVRAM-gated at this precision✓ Measured

Image Editing images/min 2

WorkloadResultTelemetryData
FLUX.1 Kontext dev✕ Won't fit needs ~26 GBVRAM-gated at this precision✓ Measured
Qwen-Image-Edit✕ Won't fit needs ~42 GBVRAM-gated at this precision✓ Measured

Video Generation frames/s 2

WorkloadResultTelemetryData
LTX-Video (distilled)✕ Won't fit needs ~14 GBVRAM-gated at this precision✓ Measured
Wan 2.2 5B (720p)✕ Won't fit needs ~18 GBVRAM-gated at this precision✓ Measured
How we measured this. Every result comes from our own pinned, reproducible AI suite, 12 workloads: the Qwen3-4B to Llama-70B LLM ladder (llama.cpp, Q4_K_M), SDXL / Z-Image / FLUX-dev generation, FLUX-Kontext / Qwen-Edit editing, and LTX / Wan video, run first-party on rented hardware with under 0.5% run-to-run variance. Peak VRAM, power draw, temperature and tokens-per-watt are captured per workload. “Won’t fit” rows are real data: where a model exceeds the card’s VRAM at the tested precision we record a hard gate rather than silently dropping to a smaller quant. Measured 2026-07-11 · harness 2.0.0-standalone.

GeForce RTX 4060 specifications

ArchitectureAda Lovelace
CUDA cores3,072
VRAM8GB GDDR6
Memory bus128-bit
Memory bandwidth272 GB/s
Boost clock2,475 MHz
TDP115 W
Process4nm
InterfacePCIe 4.0 x16
Release date2023-05-24
Launch MSRP$299

Verdict, capable, but 8GB sets the ceiling

GeForce RTX 4060 scores 1.9/100, #92 of 102. It ran 3 of 12; 9 exceeded its 8GB. Every figure here is our own measurement.

Relative performance: where the GeForce RTX 4060 lands

100% = this card, AI & Machine Learning headline metric (AI Score). #52 of 61 desktop cards in this vertical.

GPURelative%AI Score
Intel Arc B580
105%2
NVIDIA GeForce RTX 2060 Super
100%1.9
NVIDIA GeForce RTX 2070
100%1.9
NVIDIA GeForce RTX 3050
100%1.9
GeForce RTX 4060
100%1.9
NVIDIA GeForce RTX 5050
100%1.9
Intel Arc A750
100%1.9
AMD Radeon RX 7600
95%1.8
NVIDIA GeForce GTX 1080
95%1.8

Same card, other workloads: GeForce RTX 4060 Gaming benchmarks

← All AI & Machine Learning GPU rankings

The silicon

Transistors18,900 million
Die size158.7 mm²
Process node4 nm
Fabricated byTSMC
Transistor density119.1 million per mm²

Denser than 76% of the 76 cards we have silicon data for. Density is the clearest measure of what a process node bought: a card that gained it without growing the die got its speed from the fab rather than the architecture.

Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.

What this card can build

Whole-job timings, composed from our measured per-model results on this card.

Can't run: 60-second AI short film (needs Qwen3 32B), 60-second AI short film, narrated (needs Qwen3 32B), 10 short social clips (needs Qwen3 32B), 40-product photo shoot (needs FLUX.1 Kontext dev), 6-panel comic page (needs Qwen3 32B), 20 long-form articles (needs Llama 3.3 70B), Full codebase review (needs Qwen2.5-Coder 14B), Character sheet, 12 poses (needs FLUX.1 dev), 100-photo restoration batch (needs FLUX.1 Kontext dev), 24-frame storyboard (needs Qwen3 32B), 100-photo restore and enlarge (needs FLUX.1 Kontext dev).