Kandinsky 3 on Annapurna Labs Alpine AL324 NAS (4 GB)

Can the Annapurna Labs Alpine AL324 NAS (4 GB) run Kandinsky 3?

No, it doesn’t fit

No. Kandinsky 3 needs about 4.2 GB even at FP16; the Annapurna Labs Alpine AL324 NAS (4 GB) has 2.0 GB usable.

Download Kandinsky 3

Original weights · Hugging Face

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

huggingface.co/kandinsky-community/kandinsky-3 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/ai-forever/Kandinsky-3 (opens in a new tab)

git clone https://github.com/ai-forever/Kandinsky-3

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 6/100 (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 Won't run: How well it runs on the Annapurna Labs Alpine AL324 NAS (4 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.	6.5 / 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.	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	6.5 / 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 Annapurna Labs Alpine AL324 NAS (4 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	4.2 GB	2.0 GB	—	—	Won't run	48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Hardware that can run it

48Fair quality (C) · 48 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 GeForce RTX 5090 FP16 · 7.5 s · Runs great
48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER FP16 · 18 s · Runs well (encoder in RAM)
48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell FP16 · 6.6 s · Runs great
48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT FP16 · 13 s · Runs great (encoder in RAM)
48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 FP16 · 13 s · Runs great (encoder in RAM)
48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER FP16 · 13 s · Runs great (encoder in RAM)

Models that do run on the Annapurna Labs Alpine AL324 NAS (4 GB)

39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. SDXL Turbo FP8 · 73 s
42Fair quality (C) · 42 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. Realistic Vision V5.1 FP16 · 10.8 min
28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. SD Turbo FP16 · 43 s
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. DreamShaper 8 FP16 · 10.8 min
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. Stable Diffusion 1.5 FP16 · 10.8 min

Quick answers

How much memory does Kandinsky 3 need on the Annapurna Labs Alpine AL324 NAS 4GB?

Even at FP16 it needs about 4.2 GB; the Annapurna Labs Alpine AL324 NAS 4GB has 2.0 GB usable.

What can the Annapurna Labs Alpine AL324 NAS 4GB run instead?

SDXL Turbo, Realistic Vision V5.1 and SD Turbo run best on it; the page lists more, each with its speed.

What hardware can run Kandinsky 3?

RTX 5090 32GB, RTX 4070 SUPER 12GB and NVIDIA RTX PRO 6000 Blackwell 96GB 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.