Short answer: HelixSR, an unofficial mod that runs NVIDIA’s DLSS Model E (the CNN model associated with DLSS 3.7) on AMD graphics, has shown lower upscaler-processing time than an unofficial FSR 4 implementation in one Steam Deck comparison. That does not make it a universal winner. HelixSR is experimental, works only in particular Direct3D 12 and Proton configurations, has mixed image-quality reports, and is not official DLSS support for Steam Deck or other AMD handhelds.
The most defensible conclusion is conditional: try HelixSR when a Direct3D 12 game and your device meet its requirements and you are willing to troubleshoot. Keep the game’s native upscaler or an FSR 4 workaround available, because compatibility, temporal stability, frame pacing, power use and visual quality can vary by title.
As an Amazon Associate I earn from qualifying purchases.
What HelixSR actually is
HelixSR is a community project that presents NVIDIA DLSS Model E as a drop-in FSR 3.1 upscaler for Direct3D 12 games. It executes the neural upscaling work as ordinary Direct3D 12 compute shaders on AMD GPUs. It does not use NVIDIA Tensor Cores, an NVIDIA driver, CUDA or ROCm. The project maintainers explicitly describe it as independent and unofficial: “HelixSR is an independent, unofficial project and is not affiliated with or endorsed by NVIDIA, AMD or the OptiScaler project.”
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
In practical terms, this is a translation and replacement layer, not a hidden AMD version of NVIDIA’s supported DLSS stack. The name “DLSS 3.7” refers to the Model E network associated with that DLSS generation; installing HelixSR does not give an AMD handheld NVIDIA’s driver-level DLSS implementation, frame-generation stack or vendor support.
#1 Best Overall
- 1TB NVMe SSD
- 1280 x 800 HDR OLED display with premium anti-glare etched glass, 7.4" Diagonal display size up to 90Hz refresh rate
- Wi-Fi 6E
- 50Whr battery; 3-12 hours of gameplay (content-dependent)
- Carrying case with removable liner
FSR 4 in the comparisons discussed here is also not necessarily an official, integrated implementation on Steam Deck. Reports describe an unofficial FSR 4 workaround. Treat both sides of the comparison as software projects whose behavior depends on the game, API, operating system, driver and replacement layer.
HelixSR and official DLSS are different products
- Official DLSS: NVIDIA’s supported technology, normally integrated for compatible NVIDIA hardware and drivers.
- HelixSR: an experimental community implementation of Model E through Direct3D 12 compute shaders on AMD hardware.
- Official AMD ML-based FSR: AMD’s own technology, with current official availability stated for Radeon RX 7000 and RX 9000 graphics; AMD says RX 6000 support is planned for 2027.
Calling HelixSR “DLSS on Steam Deck” is therefore shorthand for an unofficial model implementation. It should not be read as NVIDIA endorsing AMD handheld support.
Compatibility: the deciding factor before performance
HelixSR’s repository lists experimental support for AMD RDNA 1 and newer GPUs, with Vega described as experimental. The maintainers developed and tested it on an AMD BC-250 under Linux with Mesa RADV. They state that other GPUs and Windows were not tested by them. That narrow test statement matters: a project that runs on one AMD configuration is not automatically validated on every Steam Deck, Windows handheld or desktop Radeon card.
| Compatibility area | What is established | What remains uncertain |
|---|---|---|
| Game API | Direct3D 12 is the target API in the project documentation. | The reported implementation does not support Vulkan. |
| Linux | Project documentation describes use through Proton; secondary coverage reports use with vkd3d-proton. | Results can change with Proton, vkd3d-proton, Mesa and game updates. |
| Windows | Windows is documented as a target platform. | Maintainers say Windows was not tested in their own development statement. |
| AMD hardware | RDNA 1 and newer are listed; Vega is experimental. | Universal support across GPUs, APUs and handheld power profiles is not established. |
| Game integration | HelixSR presents itself as an FSR 3.1 upscaler replacement. | Games without FSR 3.1 may require OptiScaler or another compatibility layer, according to secondary reporting. |
What this means on Steam Deck
A Steam Deck user needs a Direct3D 12 rendering path running through Proton and vkd3d-proton. A Vulkan-only title is outside the reported implementation. A game that does not expose the expected FSR 3.1 interface may also need OptiScaler, adding another point of failure. The project’s current README and release notes should be checked immediately before installation because an experimental compatibility layer can change rapidly.
What this means on Windows handhelds
Windows support is documented, but the maintainers’ own testing statement does not validate every Windows device. A handheld with a different Radeon architecture, driver branch, memory allocation, screen resolution or power limit can produce different results from Steam Deck or the BC-250 test system. Do not infer support merely from the presence of an AMD GPU.
How to evaluate a game before installing
- Confirm the rendering API. Check the game’s settings, launch options or technical documentation for Direct3D 12. If the title is running through Vulkan, the reported HelixSR implementation is not compatible.
- Check for the expected upscaler interface. HelixSR is described as a drop-in FSR 3.1 replacement. If the game lacks FSR 3.1 support, determine whether an additional layer such as OptiScaler is required.
- Record your baseline. Note the game build, Proton version, Mesa or Windows driver, output resolution, render scale, upscaling preset, GPU clock, TDP and a repeatable scene.
- Back up configuration files. Keep a copy of the game’s original upscaler files and settings so you can restore them if the mod causes crashes, black screens or broken menus.
- Test one change at a time. First run the game with its standard upscaler, then test HelixSR under the same resolution, preset and scene. Change only one variable when diagnosing a result.
There is no evidence that installing HelixSR universally improves battery life, average frame rate or frame pacing. The purpose of the baseline is to separate an upscaler change from unrelated driver, shader-cache or power-management changes.
Rank #2
- International (UK) Version
- 7.4” diagonal, HDR OLED, 1280 x 800 x RGB, up to 90Hz Refresh rate, High performance touch, <0.1 ms Response time, 1,000 nits peak brightness (HDR), 600 nits (SDR)
- SteamOS 3.0 (Arch-based)
- 512GB NVMe SSD, 16GB LPDDR5 on-board RAM (5500 MT/s quad 32-bit channels), microSD UHS-I supports SD, SDXC and SDHC
- 6 nm AMD APU, CPU: Zen 2 4c/8t, 2.4-3.5GHz (up to 448 GFlops FP32
What the Steam Deck performance numbers show
The clearest published comparison is a community Steam Deck test relayed by Digital Citizen in 2026. It measured the upscaler’s processing time, not the complete game frame time. The Steam Deck GPU was reported at 1400 MHz.
| Output resolution | HelixSR reported upscaler time | Unofficial FSR 4 reported upscaler time | Difference in that test |
|---|---|---|---|
| 800p | Approximately 3.5 ms per frame | Approximately 4.5 ms per frame | HelixSR about 1 ms faster |
| 1080p | Approximately 7 ms per frame | Approximately 11 ms per frame | HelixSR about 4 ms faster |
These are configuration-specific community measurements, not standardized independent benchmarks. They indicate that HelixSR’s upscaler pass was cheaper in that test, especially at 1080p. They do not establish a fixed percentage advantage, and they do not tell you whether the game reached a higher average frame rate, better 1% lows, steadier frame pacing or lower power draw.
A separate BC-250 result is not a Steam Deck result
Digital Citizen also relayed a community result from a BC-250 system running Hitman: World of Assassination at 4K: 35 FPS with HelixSR/DLSS Quality versus 17 FPS with FSR 4. That result involves different hardware, a different power envelope and a different measurement context from the Steam Deck timing figures. It cannot be combined with them to create a single ranking, and it should not be presented as expected performance on a Steam Deck or Windows handheld.
Why lower upscaler time may not raise your FPS
Upscaling is only one part of a frame. The game still spends time on simulation, draw calls, geometry, lighting, shadows, post-processing, memory transfers and display synchronization. If the CPU or another GPU pass is the bottleneck, saving a millisecond in the upscaler may not change the frame rate. Conversely, a faster pass can help when the upscaler is a significant portion of the GPU workload.
Frame-time arithmetic also matters. A 3.5 ms upscaler pass does not mean a 3.5 ms total frame. Reported upscaler latency should therefore be listed separately from average FPS, 1% low FPS, frame-time graphs, power consumption and temperature. Those are different measurements.
Image quality: no settled winner
Available impressions are divided. Some testers judged HelixSR better than FSR 3 but slightly behind FSR 4. Another tester thought Model E could look better than FSR 4 in particular situations. These are observations, not a controlled multi-game assessment, and they do not support a categorical “DLSS wins” or “FSR wins” claim.
Coverage also mentions a blurry-output issue on RDNA 3 under Windows that reportedly received a fix in an update. The existence of that fix does not prove the issue is resolved for every GPU, driver, game or setting. If your image looks unusually soft, test the current release, verify render resolution and preset, and compare against the game’s standard upscaler before drawing a conclusion.
What to inspect in a side-by-side comparison
- Fine foliage and grass: look for crawling detail, smeared leaves and unstable reconstruction during camera movement.
- Thin geometry: fences, wires, rails and branches reveal breakup, flicker and missing pixels.
- Text and HUD elements: examine small labels and distant signage for ringing or softness.
- Motion trails: watch moving characters, vehicles and particles for ghosting or disocclusion errors.
- Shimmer and temporal stability: pan the camera slowly across high-frequency textures rather than judging one still image.
- Highlights and transparencies: inspect specular reflections, hair, smoke, glass and water, where reconstruction errors are easy to miss in static screenshots.
Use the same game frame and a matched moving sequence at the same output resolution and equivalent input resolution. Include native rendering or the game’s standard upscaler where feasible. A single sharp screenshot can hide motion artifacts; a single moving clip can hide fine-detail differences.
A fair test plan for Steam Deck and AMD handhelds
If you want a result that is useful beyond your own save file, keep the following variables fixed:
Free tools Windows power users keep installed
One-click scans. No signup required.
- Identical game build, scene, weather and camera route.
- Identical device power limit, GPU clock and performance profile.
- Identical operating-system build, driver or Mesa version and Proton/vkd3d-proton version.
- Identical output resolution, render resolution and quality preset.
- Identical frame-rate cap, refresh rate and synchronization settings.
- Identical shader-cache state and a repeatable warm-up period.
Record at least average FPS, 1% lows, frame-time behavior, upscaler processing time, GPU utilization, temperature and package power. Capture the same sequence for HelixSR, the unofficial FSR 4 implementation, the game’s normal upscaler and native rendering when performance permits. Label the hardware clearly: Steam Deck, a Windows AMD handheld and a BC-250 are not interchangeable test platforms.
Why output resolution changes the result
At a higher output resolution, the upscaler has more pixels to process. That is consistent with the reported Steam Deck timings rising from approximately 3.5 to 7 ms for HelixSR and from approximately 4.5 to 11 ms for unofficial FSR 4 when moving from 800p to 1080p. The scaling is not a guarantee for another game or driver; reconstruction cost can also depend on input resolution, motion-vector quality and implementation details.
Installation and stability precautions
Because HelixSR replaces or intercepts an upscaler interface, installation can affect launch behavior and future game updates. Use the project’s current README and release notes for the exact files and procedure rather than relying on an old guide. The documented project version is 1.9.0 and is labeled experimental, but the correct release for your game may change.
Rank #4
- 【Upgraded】We sells product with professionally upgraded to 2TB SSD. Original Seal is opened for upgrade ONLY.
- 【Stunning 7.4" HDR OLED & 90Hz Motion】 Experience striking contrast and brilliant clarity with the all-new 7.4-inch HDR OLED display. Designed from the ground up for gaming, it features a 90Hz refresh rate for smooth motion and pure blacks. This handheld is capable of delivering an immersive visual experience, ensuring your Steam library looks better than ever with vibrant colors and amazing motion rendition.
- 【30-50% More Battery & Efficient Performance】 Play your favorites longer with up to 50% more battery life. By fitting a larger battery and a power-efficient OLED panel, this device provides extended gameplay sessions. It’s the perfect travel companion for long flights or commutes. The updated AMD APU ensures high-speed performance for AAA titles while maintaining incredible energy efficiency.
- 【3X Faster Downloads with Wi-Fi 6E】 Never wait for a game again. Equipped with Wi-Fi 6E, this Steam Deck OLED offers increased bandwidth and lower latency, delivering downloads up to 3 times faster than previous models. This ensures stable online play and rapid updates, making it the most reliable wireless gaming handheld for modern high-speed home networks.
- 【Responsive Touch & Enhanced Connectivity】 Enjoy a vastly improved touchscreen with higher fidelity and faster haptics. We’ve added a dedicated Bluetooth antenna to improve connections for multiple controllers. Whether using the built-in trackpads or the included external controller, this allows for precision play in everything from FPS to complex strategy games.
- Install or update the required Proton and graphics-driver components for your device.
- Make a backup of the original game files that will be changed or overridden.
- Apply the HelixSR files exactly as the current project documentation specifies for Linux/Proton or Windows.
- Launch a test save with conservative settings and verify that the game reaches gameplay, not merely the title screen.
- Check image quality while moving the camera, then monitor frame times rather than relying only on the FPS counter.
- If the game crashes or renders incorrectly, remove the replacement files, restore the backup and retest the unmodified game.
Do not assume that a successful launch means the mod is functioning correctly. A game can silently fall back to another upscaler, produce a soft image, or lose motion-vector data while still displaying a frame.
PC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchTroubleshooting common failure modes
The game will not launch
Restore the original files first. Then verify that the title is actually using Direct3D 12 and that the Proton or Windows path matches the project’s current instructions. A game update may have changed DLL loading or the expected FSR interface.
The image is black, extremely soft or full of artifacts
Check output and render resolutions, disable conflicting overlays or replacement layers, and compare with the standard upscaler. On Windows RDNA 3 systems, confirm that you are using a release containing the reported blur fix, while recognizing that the fix is not proof of universal resolution.
There is no performance gain
Measure the upscaler pass separately from total frame time. If the CPU, simulation or another GPU pass dominates, a cheaper upscaler may not increase FPS. Also verify that the game did not fall back to a different mode and that both tests use the same power and clock settings.
The game uses Vulkan
The reported HelixSR implementation does not support Vulkan. Do not force a Direct3D 12 comparison by mixing APIs; use the game’s supported upscaler or wait for documented Vulkan support.
Quick wins for a faster PC:
Repair Windows errors before they cause bigger problemsFix Now →Scan for outdated or missing drivers - takes under a minuteDriver Scan →The game has no FSR 3.1 option
Secondary coverage says such games may need OptiScaler. That adds compatibility risk and should be tested as a separate variable. If the additional layer is unstable, the practical choice may be the game’s native upscaler.
Best Value
- 512 GB NVMe SSD: Fast storage for quicker game load times and space for larger game libraries.
- OLED Display: 1200x800 resolution with deep contrasts and vibrant colors for a captivating visual experience.
- Custom AMD APU: Power-efficient Zen 2 CPU and RDNA 2 GPU for desktop-level gaming performance.
- Expandable Storage: Add more space with a microSD card slot, ensuring you can bring even more games with you.
- Versatile Controls: With built-in thumbsticks, trackpads, and touchscreen controls, you have full control over your gaming experience.
How AMD’s official FSR roadmap fits in
AMD’s current feature page says ML-based FSR Upscaling is available on Radeon RX 7000 and RX 9000 graphics and that RX 6000 support is planned for 2027. It describes enabling the feature through supported game integration or, for certain supported games, AMD Software DLL swapping. That information does not establish an official Steam Deck implementation.
Windows Central reported on October 8, 2026, that AMD Senior Vice President and General Manager Jack Huynh described a plan to bring FSR 4 to laptops, APUs and handhelds before 2027, including a lighter model for handheld APUs. The report does not specify final handheld products, release dates, software delivery method, performance or image quality. Treat it as a roadmap statement, not as evidence that a particular Steam Deck model already supports official FSR 4.
Consequently, current Steam Deck users should distinguish three things: an unofficial HelixSR mod available to test now, an unofficial FSR 4 workaround, and AMD’s future official support plans. They are not interchangeable.
Recommended Free Tools
Which option makes sense for you?
| Your priority | Most sensible approach | Reason |
|---|---|---|
| Lowest possible upscaler overhead on a compatible Direct3D 12 game | Try HelixSR and measure it against the same game settings. | The Steam Deck comparison reported lower upscaler time for HelixSR at both 800p and 1080p. |
| Predictable installation and vendor support | Use the game’s supported upscaler or native rendering. | HelixSR is independent, unofficial and experimental. |
| Best image quality in one specific game | Compare moving footage at matched resolutions. | Reports disagree, and image quality varies by scene and implementation. |
| A Vulkan title | Use the title’s supported path. | The reported HelixSR implementation does not support Vulkan. |
| Buying a handheld for future FSR support | Wait for confirmed device and software details. | AMD’s reported roadmap does not establish final products, dates or performance. |
Do not buy a new handheld solely to run this mod. The evidence does not show that one Steam Deck model or AMD handheld is universally better, and a software experiment can be tested on compatible hardware you already own.
Bottom line
HelixSR can be faster than an unofficial FSR 4 implementation in the narrow Steam Deck measurements currently reported: approximately 3.5 versus 4.5 ms at 800p and approximately 7 versus 11 ms at 1080p with the GPU reported at 1400 MHz. A separate 4K BC-250 result also favored HelixSR, but it is not a Steam Deck benchmark.
Those figures are useful signals, not a universal verdict. Compatibility is limited to particular Direct3D 12 paths, Linux/Proton or Windows configurations, and AMD hardware; Vulkan is not supported in the reported implementation. Image-quality impressions conflict, and no broad standardized testing establishes a winner. Test per game, keep a rollback path, and judge total frame time and moving-image quality—not the upscaler milliseconds alone.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
