Cosmos3-Nano-NVFP4

wfen/Cosmos3-Nano-NVFP4

Cosmos3-Nano-NVFP4 is a machine learning model from wfen. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as openmdw-1.0.

Weight-only NVFP4 (E2M1, block 16) + AWQ quantization of the Cosmos3OmniTransformer for Cosmos3-Nano, delivered as safetensors. The transformer drops from ~30 GB (bf16) to ~9 GB; VAE, vision encoder, tokenizers, and s…

Downloads · 30 days

8% of all-time downloads

All-time downloads

Public

Repo size

14 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors13.9 GB · 99%

At a glance

Library: diffusers
License: openmdw-1.0
Model type: cosmos3_omni
Access: Public
Created: Jun 20, 2026
Updated: Jul 3, 2026
SHA: b2845235

Base models

nvidia/Cosmos3-Nano

Model card

From the Hugging Face model README

Cosmos3-Nano — NVFP4-AWQ (safetensors)

Weight-only NVFP4 (E2M1, block 16) + AWQ quantization of the Cosmos3OmniTransformer for Cosmos3-Nano, delivered as safetensors. The transformer drops from ~30 GB (bf16) to ~9 GB; VAE, vision encoder, tokenizers, and scheduler remain bf16. Runs the diffusers Cosmos3OmniPipeline (fake-quant) on a single RTX 5090 (32 GB, sm_120).

Load

from load_quantized import load           # self-contained; needs torch, diffusers, modelopt, safetensors
pipe = load(".")                           # this directory; requires a Blackwell GPU at load (FP4 capability check)
import torch
with torch.autocast("cuda", torch.bfloat16):
    img = pipe("a corgi astronaut", num_frames=1, height=480, width=480).video[0][0]
img.save("out.png")

Format (Path B)

The transformer is serialized as safetensors plus a tiny structural sidecar:

File	Contents
`transformer/diffusion_pytorch_model.safetensors`	505 weight-only NVFP4 weights + scales + the AWQ smoothing scales + bf16 keep-modules (≈2829 tensors)
`transformer/modelopt_state.pt`	tensor-free ModelOpt structural state (quantizer layout) — needed to rebuild the quantizer modules
`transformer/config.json`	transformer config (`action_gen=false`)
`quantization_config.json`	recipe, exclusions, and a `scale_layout` summary (see the layout note below)

Load = from_config (action_gen=False) → modelopt.torch.opt.restore_from_modelopt_state → load_state_dict(strict=True), on CPU, then move the whole pipeline to the GPU. The loader reads only the safetensors + sidecar — never the .pt. NVFP4 restore is device-order-sensitive (CPU-restore-then-.to(device)) and requires a Blackwell GPU at load time (FP4 capability check).

NVFP4 scale layout (authoritative; per quantized Linear)

tensor	shape (example, in=4096)	dtype	role
`…weight`	`(out, in/2)`	uint8	packed FP4 E2M1 (2 codes / byte)
`…weight_quantizer._scale`	`(out, in/16)`	E4M3	per-block-16 scale
`…weight_quantizer._double_scale`	`()`	float32	per-tensor FP32 global scale
`…weight_quantizer._amax`	`()`	bf16	per-tensor amax
`…input_quantizer._pre_quant_scale`	`(in,)`	bf16	AWQ smoothing (weight-only)

Recipe & scope (INV-2 / INV-4)

Weight-only NVFP4 (E2M1, block 16, per-block E4M3 scale + per-tensor FP32 global) with AWQ calibration (awq_lite; activation quantizers disabled). Quantized: self_attn.*, mlp.*, mlp_moe_gen.*, lm_head (505 Linears). Kept bf16: token embeddings, all norms, time_embedder, proj_in/proj_out, audio/action adapters. Calibration: 64 prompts (3 bundled + 61 curated physical-AI), 8 denoising steps, seed 123.

Quality

Verified by equivalence to the reference NVFP4 checkpoint on EC-01..06 against the frozen Session-1 band (M2 LPIPS ≤ τ_nvfp4 = 0.5463 and mean SSIM ≥ 0.90, no catastrophic artifacts), plus a bitwise safetensors==.pt weight round-trip. NVFP4 ≠ reference bitwise by design (our AWQ calibration set differs from the reference's unshipped set).

Library: diffusers
Type: cosmos3_omni
License: openmdw-1.0
Created: Jun 20, 2026
Updated: Jul 3, 2026