NVIDIA4B~3 GB VRAM at BF16

Cosmos 3 Edge — VRAM, speed & local setup

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

Written by Jakub Rusinowski · Last updated July 21, 2026

The on-device tier — a 4B-parameter open world model on a dense 2B backbone that runs vision reasoning and robot-action generation directly on the robot, with no cloud round-trip. Released mid-July 2026, Edge targets NVIDIA Jetson (including the new Jetson T2000/T3000 modules) and RTX GPUs; NVIDIA cites a GeForce RTX 3070 or better as a local prototyping on-ramp. On Jetson Thor it generates 32 actions per inference at 15 Hz real-time control. Weights are ~8 GB at BF16, so it fits a single consumer or embedded GPU. This is the practical tier for hobbyist and edge robotics. Omnimodal reasoning + action. OpenMDW-1.1. Specs from launch coverage and the Hugging Face model card — verify before relying on them.

Cosmos 3 Edge needs about 3 GB of VRAM at BF16 — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Logic78

Creative80

Coding28

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Weights plus overhead only: this model's architecture is unpublished, so no KV cache is added.

Quant	VRAM	Speed (est.)	Fit
Q2_K 2.63 bpw	2.1 GB	~269 tok/s	Fits
Q3_K_M 3.41 bpw	2.5 GB	~252 tok/s	Fits
Q4_K_M 4.83 bpw	3.2 GB	~225 tok/s	Fits
Q5_K_M 5.67 bpw	3.6 GB	~212 tok/s	Fits
Q6_K 6.56 bpw	4.1 GB	~199 tok/s	Fits
Q8_0 8.50 bpw	5.1 GB	~177 tok/s	Fits
F16 16.00 bpw	8.8 GB	~123 tok/s	Fits

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Cosmos 3 Edge VRAM calculator →

Get Cosmos 3 Edge running

The cheapest catalogued GPU that runs Cosmos 3 Edge is the Intel Arc B570 (10 GB).

Buy this hardware Intel Arc B570 10GB — 10 GB VRAM · 150 W board power Deploy in the cloud now RTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.

Intel Arc B570 10GB

10 GB VRAM · 150 W board power

2026 prices are volatile — check the current listing.

Check price on Amazon

How to run Cosmos 3 Edge

Install Ollama, then run:

$ollama run cosmos-3

Weights on Hugging Face: nvidia/Cosmos3-Edge ↗

Specifications

Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.

Parameters: 4B total (2B dense transformer backbone)
Context window: Omnimodal I/O (video/action)
Architecture: Two-tower Mixture-of-Transformers — autoregressive reasoner (VLM) + diffusion generator, shared multimodal attention
Provider: NVIDIA
Licence: OpenMDW-1.1
Practical deployment: Edge device (phone, SBC)
Specified at: BF16
System RAM: 16 GB
Record updated: 2026-07-21

LicenceOpenMDW-1.1Commercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best foredge roboticson devicereal time controljetsonprototyping

Can I run Cosmos 3 Edge on my GPU?

Other Cosmos 3 sizes

Cosmos 3 Edge — frequently asked questions

How much VRAM does Cosmos 3 Edge need?

About 3 GB at BF16 — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does Cosmos 3 Edge run on an RTX 4090 (24 GB)?

Yes. Cosmos 3 Edge needs about 3 GB at BF16, inside a 24 GB card, at an estimated 225 tokens/sec.

How do I run Cosmos 3 Edge locally?

Install Ollama and run `ollama run cosmos-3`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does Cosmos 3 come in?

Cosmos 3 Super (39 GB), Cosmos 3 Nano (10 GB), Cosmos 3 Edge (3 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.