What GPU do I need to run Felldude/MiniMaxImage_hdr_diffusers_vae?

584M parameters, published in F32. View on Hugging Face

584M
Parameters
F32
Native precision
Unknown
Architecture
text-generation
Pipeline

MiniMaxImage_hdr_diffusers_vae is published by Felldude on Hugging Face, with 498 downloads and 23 likes to date. It's a unlisted-architecture model built for text-generation, published natively in F32.

VRAM required & cheapest live GPU fit

Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP322.2 GB2.6 GBRTX 30701$0.088/hr
FP8 (quantized)0.5 GB0.7 GBRTX 5060 Ti1$0.180/hr
INT4 (quantized)0.3 GB0.3 GBRTX 30701$0.088/hr

A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.

INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.

Cheapest way to run MiniMaxImage_hdr_diffusers_vae at its published (F32) precision: 1× RTX 3070, at $0.088/hr per GPU ($0.088/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.

MiniMaxImage_hdr_diffusers_vae: common questions

How much VRAM does MiniMaxImage_hdr_diffusers_vae need?

2.6 GB at FP32, 0.7 GB at FP8 (quantized), 0.3 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 2.2 GB of weights plus inference overhead is the whole requirement.

Can MiniMaxImage_hdr_diffusers_vae run in 16-bit instead of FP32?

Yes. Its published weights are FP32, 2.2 GB, or 2.6 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 1.1 GB, or 1.3 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.

How many copies of MiniMaxImage_hdr_diffusers_vae fit on one RTX 3070?

3, by VRAM alone. That card carries 8.0 GB and one copy needs 2.6 GB at FP32, on a live rate of $0.088/hr for the whole card. Throughput is not modelled here, so 3 copies is not 3 times the requests served.

Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.

More MiniMax H3 models

All 8 MiniMax H3 models: VRAM and GPU requirements

More on MiniMaxImage_hdr_diffusers_vae

Related reading: RTX 3070 pricing and specs, How much VRAM you need for LLMs, What AI inference is, and What AI model fine-tuning is.

ComfyUI on our compute

Rent a GPU with ComfyUI already installed. Your custom nodes and models are there next time.

$29 a month, or pay as you go

Start ComfyUI

Start ComfyUI on a rented GPU.

Sign up in 60 seconds. Pay for the GPU minutes you actually use.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.