NVIDIA TITAN X (Pascal), AI & Machine Learning Benchmarks & Specs

12GB · AI Score 2.5/100 · anchored estimate vs 51 measured cards

2.5 AI Score Includes estimates

We have not run NVIDIA TITAN X (Pascal) on our bench. These figures are anchored estimates, interpolated per workload against the 51 GPUs we did measure. On Llama 3.1 8B (Q4_K_M) NVIDIA TITAN X (Pascal) should deliver about 90.6 tokens/sec. Llama 3.3 70B does not fit. It needs roughly 42GB and this card has 12GB. For image generation, SDXL should run near 0.48 it/s, while FLUX.1-dev won't fit at BF16 (needs ~26GB). 8 of the 12 workloads won't fit on 12GB at the tested precision, Qwen3 32B, Llama 3.3 70B, Z-Image Turbo, FLUX.1-dev and others. We publish those as hard gates rather than quietly dropping to a smaller quant.

AI & Machine Learning benchmark results

Text Generation tok/s 5

Qwen3 4B147.2
Llama 3.1 8B90.6
Qwen2.5-Coder 14B44.8
WorkloadResultTelemetryData
Qwen3 4B147.2 tok/sestimatedEst.
Llama 3.1 8B90.6 tok/sestimatedEst.
Qwen2.5-Coder 14B44.8 tok/sestimatedEst.
Qwen3 32B✕ Won't fit VRAM-gated at this precisionEst.
Llama 3.3 70B✕ Won't fit VRAM-gated at this precisionEst.

Image Generation images/min 3

WorkloadResultTelemetryData
Stable Diffusion XL0.96 images/minestimatedEst.
Z-Image Turbo✕ Won't fit VRAM-gated at this precisionEst.
FLUX.1 dev✕ Won't fit VRAM-gated at this precisionEst.

Image Editing images/min 2

WorkloadResultTelemetryData
FLUX.1 Kontext dev✕ Won't fit VRAM-gated at this precisionEst.
Qwen-Image-Edit✕ Won't fit VRAM-gated at this precisionEst.

Video Generation frames/s 2

WorkloadResultTelemetryData
LTX-Video (distilled)✕ Won't fit VRAM-gated at this precisionEst.
Wan 2.2 5B (720p)✕ Won't fit VRAM-gated at this precisionEst.
How this estimate is derived. This card hasn’t been through our bench yet, so its numbers are anchored estimates, interpolated from the 51 first-party measured cards (LLM: bandwidth Theil-Sen ladder · diffusion/video: tensor-throughput ladder within architecture family · gates: realistic Q4/BF16 VRAM floors). The VRAM “won’t fit” gates are exact, since they’re pure capacity limits. Estimates are replaced with measured data as more silicon goes through the bench. Full methodology →

NVIDIA TITAN X (Pascal) specifications

ArchitecturePascal (GP102)
CUDA cores3,584
VRAM12GB GDDR5X
Memory bus384-bit
Memory bandwidth480 GB/s
Boost clock1,531 MHz
TDP250 W
Process16nm
InterfacePCIe 3.0 x16
Release date2016-08-02
Launch MSRP$1,200

Verdict, capable, but 12GB sets the ceiling

NVIDIA TITAN X (Pascal) scores 2.5/100, #76 of 102. It ran 4 of 12; 8 exceeded its 12GB. Figures are anchored estimates, not measurements, we flag that on every row.

Relative performance: where the NVIDIA TITAN X (Pascal) lands

100% = this card, AI & Machine Learning headline metric (AI Score). #37 of 61 desktop cards in this vertical.

GPURelative%AI Score
GeForce GTX 1080 Ti
104%2.6
NVIDIA GeForce RTX 3060
104%2.6
NVIDIA TITAN Xp
104%2.6
AMD Radeon RX 7700 XT
100%2.5
NVIDIA TITAN X (Pascal)
100%2.5
AMD Radeon RX 6700
92%2.3
NVIDIA GeForce RTX 3080
92%2.3
NVIDIA GeForce RTX 2080 Ti Founders Edition
88%2.2
NVIDIA GeForce RTX 3070 Ti
88%2.2

Same card, other workloads: NVIDIA TITAN X (Pascal) Gaming benchmarks

← All AI & Machine Learning GPU rankings

What this card can build

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

WorkflowTimeEnergyBasis
Full codebase review22.3 minn/aestimate, 0 of 1 stage measured

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), 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).