thesysdev·DiffusionGemmaForBlockDiffusion

OUI 1 — Hardware Requirements & GPU Compatibility

ChatVision

OUI 1 is a 25.8B-parameter open language model from thesysdev. It supports a context window of up to 262,144 tokens. At BF16 it needs about 52.29 GB of VRAM — see which GPUs and Macs can run it below.

2.9K downloads 131 likes262K context

Specifications

Publisher
thesysdev
Parameters
25.8B
Architecture
DiffusionGemmaForBlockDiffusion
Context Length
262,144 tokens
Vocabulary Size
262,144
Release Date
2026-09-07
License
Apache 2.0

Get Started

HuggingFace

thesysdev/OUI-1

How Much VRAM Does OUI 1 Need?

Select a quantization to see compatible GPUs below.

QuantizationBitsVRAM
BF16est.16.0052.3 GB

est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.

Which GPUs Can Run OUI 1?

BF16 · 52.3 GB

OUI 1 (BF16) requires 52.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 68+ GB is recommended. Using the full 262K context window can add up to 43.9 GB, bringing total usage to 96.2 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.

Which Devices Can Run OUI 1?

BF16 · 52.3 GB

22 devices with unified memory can run OUI 1, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio (M3 Ultra, 96GB).

Related Models

Frequently Asked Questions

How much VRAM does OUI 1 need?

OUI 1 requires 52.3 GB of VRAM at BF16. Full 262K context adds up to 43.9 GB (96.2 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 25.8B × 16 bits ÷ 8 = 51.6 GB

KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)

KV Cache + Overhead ≈ 44.6 GB (at full 262K context)

VRAM usage by quantization

52.3 GB
96.2 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 5090 run OUI 1?

No — OUI 1 requires at least 52.3 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.

Can I run OUI 1 on a Mac?

OUI 1 requires at least 52.3 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.

Can I run OUI 1 locally?

Yes — OUI 1 can run locally on consumer hardware. At BF16 quantization it needs 52.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is OUI 1?

At BF16, OUI 1 can reach ~92 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: NVIDIA B200 → 8000 ÷ 52.3 × 0.65 = ~99 tok/s

Estimated speed at BF16 (52.3 GB)

~99 tok/s
~99 tok/s
~92 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of OUI 1?

At BF16, the download is about 51.65 GB.

Which GPUs can run OUI 1?

No single consumer GPU has enough VRAM to run OUI 1 at BF16 (52.3 GB). Multi-GPU or professional hardware is required.

Which devices can run OUI 1?

23 devices with unified memory can run OUI 1 at BF16 (52.3 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.