Allegro (2.8B) on NVIDIA RTX PRO 6000 Blackwell

Can the NVIDIA RTX PRO 6000 Blackwell run Allegro (2.8B)?

Yes, but slowly

Slow. At FP16 it needs about 38.2 GB of 96.0 GB usable, with an estimated speed of 14.7 min.

Best precision: FP16
Memory mode: Everything on GPU
Time per clip: 14.7 min
Output: 1280×720, 88 frames, 100 steps

Download Allegro (2.8B)

Original weights · Hugging Face

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

huggingface.co/rhymes-ai/Allegro (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/rhymes-ai/Allegro (opens in a new tab)

git clone https://github.com/rhymes-ai/Allegro

Links checked 9 hours ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at FP16, 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 Slow: How well it runs on the NVIDIA RTX PRO 6000 Blackwell: 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.	23.4 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	6.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	9.2 / 15
Match score	64.4 / 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 NVIDIA RTX PRO 6000 Blackwell

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	38.2 GB	96.0 GB	14.7 min	Everything on GPU	Slow	52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Other hardware that runs it

52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP16 · 17.6 min · Slow (tight fit · encoder in RAM)
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. AMD Ryzen AI Max+ 395 (128 GB) FP16 · 38.4 min · Slow
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA L40S FP16 · 18.5 min · Slow
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX 6000 Ada Generation FP16 · 18.6 min · Slow
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA L40 FP16 · 18.7 min · Slow
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon PRO W7900 FP16 · 22.3 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.