Cosmos-Predict2 14B Video2World on Intel Xeon Silver (4100 to 4300 series) NAS (32 GB)

Can the Intel Xeon Silver (4100 to 4300 series) NAS (32 GB) run Cosmos-Predict2 14B Video2World?

Barely: it runs very slowly (tight fit · CPU offload)

Very slow (tight fit · CPU offload). At FP8 it needs about 24.7 GB of 26.2 GB usable, with an estimated speed of 25.6 h.

Best precision: FP8
Memory mode: Sequential CPU offload
Time per clip: 25.6 h
Output: 1280×704, 93 frames, 35 steps

Download Cosmos-Predict2 14B Video2World

Original weights · Hugging Face

Full-precision files from NVIDIA, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/nvidia/Cosmos-Predict2-14B-Video2World (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Official repo · GitHub

Reference code, inference scripts and docs from NVIDIA. The weights themselves download from Hugging Face.

github.com/nvidia-cosmos/cosmos-predict2 (opens in a new tab)

git clone https://github.com/nvidia-cosmos/cosmos-predict2

Links checked 11 hours ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at FP8, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Very slowtight fit · CPU offload: How well it runs on the Intel Xeon Silver (4100 to 4300 series) NAS (32 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	30.9 / 45
Memory fitFull marks when the model fits in the share of the NAS’s memory that models can use (the rest stays with the NAS system and its storage services); fewer when it goes past that limit.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.7 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	56.5 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every precision on the Intel Xeon Silver (4100 to 4300 series) NAS (32 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	29.6 GB	26.2 GB	—	—	Won't run	70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	24.7 GB	26.2 GB	25.6 h	Sequential CPU offload	Very slowtight fit · CPU offload	68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Other hardware that runs it

70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell FP16 · 19.5 min · Slow
68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP8 · 26.1 min · Slow (CPU offload)
70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 80GB SXM FP16 · 18.6 min · Slow
70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H800 80GB SXM FP16 · 18.6 min · Slow
70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 80GB PCIe FP16 · 22.7 min · Slow
70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA A100 80GB PCIe FP16 · 27.8 min · Slow

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.