B

BROMANDER

STUDIOS

HomeServicesProcess
LabsBlogContact
> BROMANDER_LABS

CAN YOUR RIGTRAIN IT?

Fine-tuning eats far more memory than inference — weights, gradients, optimizer state, and activations all have to live on the card at once. Here's the honest peak VRAM for full, LoRA, and QLoRA across 50+ models.

Math runs in your browserMixed precision · fp32 master copy
01 — Model & method
02 — Batch & sequence
03 — Your hardware
Peak VRAM
QLoRA · peak training memory
6.03 GB
Trainable
8M
of total
0.10%
GPU usable
22.1 GB
Fits on one NVIDIA RTX 4090. 6.03 GB of 22.1 GB usable VRAM.
Memory breakdown
Weights · 67%Gradients · 0%Optimizer · 2%Activations · 11%Overhead · 21%
Weights
4.03 GB
Gradients
0.02 GB
Optimizer + master
0.10 GB
Activations
0.64 GB
Overhead
1.24 GB

Estimate assumes bf16 mixed precision with an fp32 master weight copy. Activation memory is approximate — it varies with attention implementation (Flash Attention lowers it) and exact model architecture.

─── Your Training Card ───

The actual image that shows on X, LinkedIn, and Facebook when you share the link.

Shareable report card preview
Live preview
Need a training pipeline built?
Talk to Bromander Studios
BROMANDER STUDIOS
BROMANDER STUDIOS

BROMANDERSTUDIOS

Pioneering digital excellence through innovative solutions and cutting-edge technology.

JOIN THE WAITLIST

COMPANY

  • Labs
  • Blog
  • Contact
  • Careers

CONTACT

  • hello@bromanderstudios.com
  • Frövi, Örebro County, Sweden

© 2026 Bromander Studios. Operated by Bromander Global AB.

Org.nr 559529-7879 · Momsreg.nr SE559529787901 · Godkänd för F-skatt.

Privacy PolicyTerms of ServiceCookie Policy