Mochi 1 Preview (10B) on LattePanda 3 Delta (8 GB)

Can the LattePanda 3 Delta (8 GB) run Mochi 1 Preview (10B)?

No, it doesn’t fit

No. Mochi 1 Preview (10B) needs about 14.7 GB even at FP8; the LattePanda 3 Delta (8 GB) has 4.0 GB usable.

Download Mochi 1 Preview (10B)

Original weights · Hugging Face

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

huggingface.co/genmo/mochi-1-preview (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/genmoai/mochi (opens in a new tab)

git clone https://github.com/genmoai/mochi

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 8/100 (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 Won't run: How well it runs on the LattePanda 3 Delta (8 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.	8.2 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	0.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	0.0 / 15
Match score	8.2 / 100

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

It doesn’t fit, so only a reduced share of the quality points counts and fit, speed and memory use score zero.

Every precision on the LattePanda 3 Delta (8 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	18.2 GB	4.0 GB	—	—	Won't run	62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	14.7 GB	4.0 GB	—	—	Won't run	60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Hardware that can run it

60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 80GB SXM FP8 · 11.5 min · Runs well
60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H800 80GB SXM FP8 · 11.5 min · Runs well
60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GH200 Grace Hopper (96 GB GPU) FP8 · 11.5 min · Runs well
62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA B200 FP16 · 11.2 min · Runs well
60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H200 141GB SXM FP8 · 11.5 min · Runs well
60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP8 · 13.8 min · Slow

Models that do run on the LattePanda 3 Delta (8 GB)

35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. AnimateDiff v3 (SD 1.5) FP16 · 31.0 min

Quick answers

How much memory does Mochi 1 Preview (10B) need on the LattePanda 3 Delta 8GB?

Even at FP8 it needs about 14.7 GB; the LattePanda 3 Delta 8GB has 4.0 GB usable.

What can the LattePanda 3 Delta 8GB run instead?

AnimateDiff v3 (SD 1.5) runs best on it; the page lists more, each with its speed.

What hardware can run Mochi 1 Preview (10B)?

NVIDIA H100 80GB SXM, NVIDIA H800 80GB SXM and NVIDIA GH200 Grace Hopper (96GB GPU) run it; the page lists more, each with its speed.

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.