Source: https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/

# Which jobs your hardware can take

The Supernet checks two separate limits before sending a job to a Fast Worker. **GPU VRAM** is the memory on the graphics card. **Host RAM** is the system memory the worker actually has, meaning what Docker, WSL2 or the hosting container gives it, not what is installed in the PC. The two are never added together. A 96 GB card with 38 GiB of usable RAM still misses the jobs that need 47 GiB, and a PC with 128 GB installed still misses them if WSL2 only gives Docker 63 GB.

Hardware isn't the only gate. A job also needs:

-   **A current worker version.** New modes need a minimum Sogni Comfy Worker release. Older workers are never offered them.
-   **Subscription-earnings opt-in** for Unlimited-plan jobs. These go only to workers whose account has opted in and accepted the current terms.
-   **The Fast network.** Linux and Windows NVIDIA workers join Fast by default. Jobs queued on Relaxed go to Relaxed workers.
-   **The model files on disk.** A worker advertises only the workflows it has downloaded and can run.

All thresholds below are **as of September 2026**. Sogni tunes them from production completion and out-of-memory data, and they change. See [Thresholds change](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#thresholds-change).

## [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#contents)Contents

-   [How RAM and VRAM are measured](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#how-ram-and-vram-are-measured): read this first if your numbers look lower than you expect.
-   [Quick reference by GPU](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#quick-reference-by-gpu)
-   [Quick reference by host RAM](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#quick-reference-by-host-ram)
-   [Per-model detail](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#per-model-detail): resolution, clip length, reference video and two-stage rules. Read this when a particular job type never reaches you.
-   [Get more jobs](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#get-more-jobs): a setup checklist.
-   [Thresholds change](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#thresholds-change)

## [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#how-ram-and-vram-are-measured)How RAM and VRAM are measured

-   **RAM is measured in GiB** (1 GiB = 1,073,741,824 bytes), not the marketing GB. 46 GiB is about 49.4 GB.
-   **The container's limit counts, not the host's total.** The worker reports the memory limit of its container (its cgroup), plus current-connection health readings of effective and total memory. The Supernet uses the **smallest** of those values.
-   **WSL2 gives Docker only half of Windows RAM by default.** On a 64 GB PC that is about 31 GiB, and a `memory=48GB` setting shows up as roughly 46 to 47 GiB. See [Get more jobs](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#get-more-jobs).
-   **VRAM is the figure the worker reports for its GPU.** Some rules use 23 GB rather than 24 GB, and 30 GB rather than 32 GB, because cards often report slightly less than their nominal size.
-   **Minimum to join the Fast network:** 16 GB of VRAM and 30 GB of reported RAM. Below those, the worker is disconnected with `Insufficient VRAM` or `Insufficient RAM`. The worker checks the RAM floor before it connects and waits instead of looping. RTX 2080, 3050, 3060, 3070 and 3080 cards, and the RTX 4070 (non-Super), are refused unless they report at least 16 GB.

## [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#quick-reference-by-gpu)Quick reference by GPU

Each column assumes the machine also meets the RAM floor in the next table.

| GPU class | Examples | What it can take |
| --- | --- | --- |
| **16 GB** | RTX 4080, 4070 Ti Super, 5080 | Image models such as Flux, Chroma, Z-Image, Krea 2 and One Obsession (Z-Image and Krea 2 up to about 2.5 MP); ACE-Step 1.5 music; upscales, which are routed to smaller cards first. No video. |
| **20 GB** | RTX 3080 20 GB class | Everything above, plus ACE-Step 1.5 XL songs up to 8 minutes |
| **24 GB** | RTX 4090, 3090 | Everything above, plus Z-Image and Krea 2 above 2.5 MP; Qwen Image Edit 2511; MiniMax Music 3; Qwen3 voice models; full-length ACE-Step XL; WAN 2.2 under 700p at 8 steps or fewer; LTX up to about 2.2 MP (1080p); **MiniMax H3 FastH3 Turbo** in every mode, including custom LoRAs and audio-guided modes; FastH3 two-stage 768p/1080p/2K for clips under 175 frames; FlashVSR |
| **32 GB** | RTX 5090 | Everything above, plus **H3 Standard, Balanced and LightX2V Turbo**; Reference-to-Video from images; **two-stage Reference-to-Video at 768p, 1080p and 2K** with reference videos, at any length; LightX2V Turbo Reference-to-Video with one reference video, inside the [RTX 5090 envelope](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#reference-to-video-with-a-reference-video); LTX up to about 4 MP (1440p); **FastH3 two-stage 768p and 1080p at any length**; LTX 10Eros; WAN at 700p+ with 8 steps or fewer, or under 700p with more than 8 steps; Pixal3D image-to-3D |
| **48 GB** | RTX 6000 Ada, L40S, A6000 | Everything above, plus FastH3 two-stage **2K** clips of 175+ frames; one-stage Reference-to-Video with a reference video, under 243 frames and up to 0.9 MP; Standard Reference clips of 342+ frames; LTX 4K; WAN 700p+ with more than 8 steps |
| **96 GB** | RTX PRO 6000 | Every job type, including one-stage Reference-to-Video with a reference video at 243+ frames or above 0.9 MP, long Balanced Reference at the full 768p canvas, and LTX-2.5 4K clips longer than 5 seconds. 80 GB data-center cards qualify for the last one too. |

The Supernet treats cards reporting **40 GB or more** as scarce capacity. See [Why 48 and 96 GB cards get certain jobs first](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#why-48-and-96-gb-cards-get-certain-jobs-first).

## [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#quick-reference-by-host-ram)Quick reference by host RAM

Usable RAM, as measured above. "Small GPU" means a card reporting 32 GB or less. Larger cards need less RAM for most MiniMax H3 and LTX work.

| Usable RAM | Small GPU (24/32 GB) | Large GPU (48/96 GB) |
| --- | --- | --- |
| **Under 30 GiB** | Not admitted to the Fast network | Not admitted |
| **30 to 38.99 GiB** | Images, music, voice, upscales, WAN, Pixal3D, and FlashVSR on cards reporting 31 GB or more. **No MiniMax H3 and no LTX.** | Everything except FastH3 two-stage 2K and the Reference-to-Video 1080p/2K cascade |
| **39 to 45.99 GiB** | Adds H3 **Standard and Balanced**: text, image, first/last-frame and Reference, plus two-stage Reference at 768p | Same as above |
| **46 to 46.99 GiB** | Adds **FastH3 Turbo** (all modes), **LightX2V Turbo** (including Reference), FastH3 two-stage 768p and 1080p, **LTX-2.3/2.5**, and FlashVSR on 24 GB cards | Same as above |
| **47 to 59.99 GiB** | Adds **FastH3 two-stage 2K** | Adds FastH3 two-stage 2K |
| **60 GiB or more** | Adds **two-stage Reference-to-Video at 1080p and 2K** | Adds two-stage Reference-to-Video at 1080p and 2K |

## [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#per-model-detail)Per-model detail

### [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#minimax-h3-minimums-by-tier)MiniMax H3: minimums by tier

| Tier | Minimum VRAM | RAM on a small GPU | RAM on a large GPU | Worker version |
| --- | --- | --- | --- | --- |
| FastH3 Turbo (text, image, first/last frame, custom LoRAs) | 23 GB | 46 GiB | 30 GiB | 1.0.193 |
| FastH3 audio-guided (image + audio, first/last + audio, audio only) | 23 GB | 46 GiB | 30 GiB | 1.0.217 |
| LightX2V Turbo (text, image, first/last frame) | 32 GB | 46 GiB | 30 GiB | 1.0.208 |
| LightX2V Turbo Reference-to-Video | 32 GB | 46 GiB | 30 GiB | 1.0.171 |
| Standard and Balanced (all modes, including Reference) | 32 GB | 39 GiB | 30 GiB | 1.0.155 and up, by mode |

Attaching a custom LoRA to an H3 job needs worker 1.0.176 or later. A Reference job with a reference video needs 1.0.177 or later.

**Windows (WSL2) exception:** LightX2V Turbo **first/last-frame** jobs go only to WSL2 workers with **more than 40 GB** of VRAM, so an RTX 5090 on Windows does not receive them. On native Linux, the 32 GB floor applies.

### [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#two-stage-output-768p-1080p-and-2k)Two-stage output (768p, 1080p and 2K)

A two-stage job renders at a half-size canvas and delivers at 2×. The canvas sets the class: a short edge up to 384 px and a long edge up to 672 px delivers **768p**, a short edge up to 544 px delivers **1080p**, and anything larger delivers **2K**.

| Two-stage job | VRAM | Host RAM | Worker version and files |
| --- | --- | --- | --- |
| FastH3, 768p/1080p class | 23 GB under 175 frames; **30 GB (the 32 GB class) at 175 frames or more** | 46 GiB on a small GPU, 30 on a large one | 1.0.217 and the H3 latent upscaler |
| FastH3, 2K class | 23 GB under 175 frames; **40 GB at 175 frames or more** | **47 GiB on every GPU** | Same |
| Reference (Standard/Balanced), 768p class | 32 GB at any length, with or without reference video | 39 GiB on a small GPU, 30 on a large one | 1.0.218 and the latent upscaler |
| Reference (Standard/Balanced), 1080p and 2K | 32 GB at any length, with or without reference video | **60 GiB on every GPU** | 1.0.220, the latent upscaler **and** the FastH3 checkpoint (CUDA 13 image) |

Long FastH3 two-stage clips (175 frames or more) need **40 GB at the 2K class** and **30 GB (the 32 GB class) at 768p and 1080p**. An RTX 5090 peaked at about 28.9 GB (768p) and 29.3 GB (1080p) on a 15-second clip, because those classes render their first pass at half size.

### [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#reference-to-video-with-a-reference-video)Reference-to-Video with a reference video

One-stage Reference-to-Video, whether Standard, Balanced or LightX2V Turbo, uses much more memory when an artist attaches a reference **video**:

-   Under 243 frames, at 0.9 MP or less: **more than 40 GB** (the 48 GB class).
-   At 243 frames or more, or above 0.9 MP (for example 1344×768): **more than 48 GB** (the 96 GB class).
-   **RTX 5090 envelope for LightX2V Turbo only:** a card named RTX 5090 with 32 GB takes the job when it has exactly one reference video, at most one reference image, no separate audio reference and no custom LoRA, and either:
    -   no reference image, up to 1120×480 pixels (537,600), up to 158 frames, with pixels × frames up to 1120 × 480 × 124; or
    -   up to 960×544 pixels (522,240) with the long side at most 960, up to 362 frames.

Two-stage Reference jobs don't follow these rules. They render the reference-conditioned pass at a quarter of the final size, so a 32 GB card takes them (see the table above).

### [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#long-reference-to-video-clips-image-references)Long Reference-to-Video clips (image references)

One-stage Standard and Balanced Reference clips of **342 frames or more** need **40 GB**. Long **Balanced** clips above **0.9 MP** need **49 GB**, which means the 96 GB class. LightX2V Turbo Reference is exempt. Two-stage Reference IDs are exempt.

### [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#ltx-23-and-ltx-25)LTX-2.3 and LTX-2.5

-   **Baseline:** 23 GB of VRAM. Host RAM must be 46 GiB on 24/32 GB cards and 30 GiB on larger ones. The rule is checked at model load, so it applies to every LTX job.
-   **Resolution:** under 30 GB, up to about 2.2 MP (1080p class). Under 40 GB, up to about 4.0 MP (1440p class). At 40 GB and above, full 4K. Size is judged on the grid-aligned size the worker actually renders.
-   **RTX 3090/4090 exception:** a desktop 3090 or 4090 (not a laptop GPU) can take **short 4K LTX-2.3** clips of up to 72 frames.
-   **Long clips (122+ frames):** above 320 frame-megapixels (width × height × frames ÷ 1,000,000) needs 30 GB, and above 600 needs 40 GB. 1080p-class clips (2.0 MP or more) longer than 360 frames need 30 GB, and 48 GB+ cards are offered them first.
-   **LTX-2.5 at 4K longer than 121 frames:** 80 GB, which means the 96 GB class.
-   **4K longer than 361 frames:** no worker class currently qualifies.
-   **LTX-2.3 10Eros:** 30 GB for every job.

### [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#wan-22)WAN 2.2

| Resolution (short side) | 8 steps or fewer | More than 8 steps |
| --- | --- | --- |
| Under 700 px | 23 GB | 32 GB |
| 700 px or more | 32 GB | 40 GB |

### [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#images-music-voice-upscaling-and-3d)Images, music, voice, upscaling and 3D

-   **Z-Image and Krea 2 family** (including Identity Edit and Dark Beast): 16 GB, or 24 GB above 2.5 MP (roughly larger than 1536×1536).
-   **Qwen Image Edit 2511:** 24 GB. The worker does not offer it, or Z-Image BF16, on RTX 30-series cards (compute capability 8.6), because those cards return corrupt images for these models.
-   **ACE-Step 1.5 XL:** 20 GB for songs up to 8 minutes, and 23 GB for longer ones. **MiniMax Music 3** and **Qwen3 voice models:** 24 GB.
-   **FlashVSR video upscaling:** 23 GB. On cards reporting under 31 GB, FlashVSR keeps its caches in host RAM and needs **46 GiB**. At 31 GB or more, the 30 GiB fleet floor applies.
-   **Image upscales** run on any card. Cards with 23 GB or more let smaller cards take them first.
-   **Pixal3D image-to-3D:** 30 GB, the CUDA 13 worker image and worker 1.0.208 (1.0.217 for multi-view). It is an optional model pack of about 15.5 GB, offered to eligible workers.

## [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#get-more-jobs)Get more jobs

### [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#1-give-the-worker-enough-ram)1\. Give the worker enough RAM

**Windows (Docker Desktop on WSL2).** Edit `%USERPROFILE%\.wslconfig` as the user who runs Docker Desktop, or answer **y** when the installer offers to update it. Then stop the worker, quit Docker Desktop, run `wsl --shutdown`, and start again.

| PC RAM | Suggested `[wsl2]` setting | About what the worker sees | What it unlocks on a 24/32 GB card |
| --- | --- | --- | --- |
| 32 GB | Default only allows ~15 GiB | Below 30 GiB | Not enough for the Fast network. Use Linux or add RAM. |
| 64 GB | `memory=48GB` | 46 to 47 GiB | All H3 tiers, LTX and FlashVSR. FastH3 2K two-stage only if the reading reaches 47. |
| 96 GB | `memory=64GB` | about 62 GiB | Everything, including the Reference 1080p/2K cascade |
| 128 GB+ | `memory=64GB` or more | 62 GiB or more | Everything |

Leave at least 16 GB for Windows on a 64 GB or larger PC, and more if you use the PC for other work. Adding swap does not raise the usable-RAM figure the Supernet checks.

**Linux, Docker, Nosana and Salad.** The Supernet reads the container's memory limit. Remove or raise any `--memory` / `mem_limit` setting, and on hosting platforms choose a container memory allocation, not just a GPU. Aim for **48 GB or more** for H3 and LTX video on a 24/32 GB card, and **64 GB** to reach every job. Some hosts report much less RAM than their GPU class suggests. For example, 96 GB confidential VMs have reported about 38 to 39 GiB, which misses FastH3 2K and the Reference cascade.

### [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#2-keep-the-worker-updated)2\. Keep the worker updated

Two-stage FastH3 needs 1.0.217, two-stage Reference 768p needs 1.0.218, and Reference 1080p/2K needs 1.0.220. Older workers are never offered these jobs. Keep persistent storage so a new model's files download once and stay.

### [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#3-opt-in-to-subscription-earnings)3\. Opt in to subscription earnings

Unlimited-plan jobs go only to workers whose account opted in and accepted the current terms at [dashboard.sogni.ai/subscription-earnings](https://dashboard.sogni.ai/subscription-earnings). Without that, the worker only receives Spark- and SOGNI-paid jobs.

### [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#4-dont-narrow-the-workflow-list-without-a-reason)4\. Don't narrow the workflow list without a reason

The worker advertises only the workflows it serves and has downloaded. Removing video workflows in **Settings**, or using a slimmer hosting preset, removes those jobs.

### [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#why-48-and-96-gb-cards-get-certain-jobs-first)Why 48 and 96 GB cards get certain jobs first

A card reporting **40 GB or more** is first offered the queued jobs whose VRAM floor is **above 32 GB**, highest floor first. Examples are long two-stage FastH3, video-referenced Reference-to-Video, LTX 4K, long LTX clips and high-step WAN. This keeps work that only a large card can do from waiting behind work any RTX 4090 or 5090 can do. It is a preference, not a filter: when no such job is queued, a large card takes ordinary work. Payment priority is taken into account too, so a large card can reach past a higher-priority ordinary job to take a job only it can run.

### [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#check-what-the-network-sees)Check what the network sees

Open your worker at [dashboard.sogni.ai/fast-workers](https://dashboard.sogni.ai/fast-workers/). The worker view shows its version and GPU, and **Worker Health** charts VRAM and host memory for the current run. See [Using the Workers Dashboard](https://docs.sogni.ai/run-a-worker/fast-worker/worker-dashboard/). On Windows, `worker-start.bat` also reports Windows RAM, Docker's usable WSL RAM and your `.wslconfig` setting. If a machine should qualify but a job type never arrives, compare its host memory with the RAM table above before restarting anything.

## [#](https://docs.sogni.ai/run-a-worker/fast-worker/hardware-requirements/#thresholds-change)Thresholds change

Every number on this page comes from the Supernet's live matching rules as of September 2026. Several are runtime settings Sogni can change without a release, including the long-clip frame counts and VRAM floors, the Balanced full-canvas rule, and the scarce-card steering. The defaults are listed above. Floors are raised when a hardware class fails jobs, and lowered when production data shows it completes them. The worker's own catalog at [api.sogni.ai/v1/worker/config/comfy](https://api.sogni.ai/v1/worker/config/comfy) lists the minimum VRAM for each model pack it downloads. Check this page again after each worker release.