Skip to content
Robotics

DreamFAR: Real-Time Robot-Object Interaction Model

1 min readupdated

Developed by Amazon-FAR, this model is designed for bimanual robot manipulation and real-time dynamics prediction using teleoperation data. It includes dynamics checkpoints, an image tokenizer, and test scenes. The solution is intended for robotics researchers and engineers working with simulation and manipulator control.

Key features

  • Acts as a world model for bimanual manipulation
  • Includes checkpoints, a tokenizer, and test scenes
  • Trained on robotic teleoperation data
  • Uses bf16 weights for inference

What you can do

  • Run the interactive demo from the project repository
  • Apply it to simulate robot actions in an environment
  • Use the attached test scenes to evaluate dynamics
hf download Amazon-FAR/dreamfar --local-dir dreamfar_assets
(cd dreamfar_assets && sha256sum -c SHA256SUMS && cd scenes && sha256sum -c SHA256SUMS)
Read moreDetails
The model is distributed under the CC BY-NC 4.0 license.
Includes a 386 MB tokenizer and a 4.4 GB dynamics model.
Requires downloading via the official Hugging Face CLI tool.
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.4 GB · ready files0.9 GB
  • FP8 / INT8recommendedweights 0.2 GB0.7 GB
  • 4-bitweights 0.1 GB0.6 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # Amazon-FAR/dreamfar
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download Amazon-FAR/dreamfar --local-dir ~/models/dreamfar
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to dreamfar
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of dreamfar (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

Amazon-FAR/dreamfar
Author
Amazon-FAR
Category
Robotics
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments