Recommended Free Tools
A GPU out-of-memory error has different fixes depending on when it occurs: while loading model weights, allocating inference cache, training, or capturing CUDA graphs. First identify the failing phase and what is using VRAM; then reduce the memory demand or adjust the specific runtime setting involved. Clearing PyTorch’s cache alone will not make room for live model allocations.
Find out when the out-of-memory error happens
Record the exact error and the step that triggers it. For a serving startup, use the logs to distinguish a failure during weight loading from one during KV-cache allocation or CUDA graph compilation and warmup. Those phases have different memory demands and remedies, as described in NVIDIA’s NIM troubleshooting guide.
Check the GPU’s total capacity and the processes using it. Also distinguish memory actively allocated by your program from memory reserved by a framework allocator. PyTorch notes that unused allocator-managed memory may still appear as used in nvidia-smi. Its memory profiler does not capture every GPU allocation: direct CUDA allocations and allocations made by other libraries, including NCCL, can fall outside its view. See PyTorch’s CUDA semantics and Understanding CUDA Memory Usage.
Do not assume every OOM is fragmentation. If weights, cache, and runtime overhead require more memory than the GPU has, allocator settings cannot create additional VRAM. Investigate fragmentation when the error or memory statistics point to substantial reserved-but-unallocated memory or inactive split blocks, and use settings documented for your installed PyTorch version.
Free tools Windows power users keep installed
One-click scans. No signup required.
#1 Best Overall
- Read Before You Buy — No Video Output: These adapters support charging and USB 2.0 data transfer, but cannot transmit video signals. Except for standard USB webcams (which use USB data only), they are not compatible with HDMI/DisplayPort cables, video-capable USB-C hubs, or docking stations with video output.
- Convert USB-A Ports to USB-C: Designed to connect USB-C earphones, cables, flash drives, card readers, and other USB-C accessories to standard USB-A ports. Plug-and-play with no drivers or software required.
- Aluminum Alloy Housing: Built with a sturdy aluminum alloy shell that aids in heat dissipation and protects against daily wear and scratches. Designed to maintain a stable and secure connection.
- Compact & Travel-Friendly: The ultra-compact design allows the adapter to stay plugged into your device without blocking adjacent ports or adding bulk, reducing wear and tear on your original USB ports.
- 12-Month Warranty: Backed by a 12-month manufacturer warranty for peace of mind. Designed to meet strict quality control standards for reliable everyday performance.
If the model fails while loading weights
Estimate weight storage from the parameter count, precision, and how the model is distributed across GPUs. NVIDIA’s heuristic is total parameters × bytes per parameter ÷ tensor parallelism. Its estimate assigns two bytes per parameter to BF16 and FP16, and one byte per parameter to FP8. These figures estimate weights only; they do not include the complete VRAM budget for cache and runtime overhead.
| NVIDIA example | Estimated weight memory | What the figure represents |
|---|---|---|
| 8-billion-parameter Llama 3.1, BF16, one GPU | 16 GB | NVIDIA’s estimate in its current NIM troubleshooting guide, accessed in 2026. The guide says the example fits on a 24 GB GPU with room for KV cache and overhead; that is not a guarantee for every runtime or workload. |
| 70-billion-parameter Llama 3.3, BF16, four GPUs | 35 GB per GPU | NVIDIA’s estimated weight memory per GPU in its current NIM troubleshooting guide, accessed in 2026. |
| 70-billion-parameter Llama 3.3, FP8, two GPUs | 35 GB per GPU | NVIDIA’s estimated weight memory per GPU in its current NIM troubleshooting guide, accessed in 2026. |
If the estimate exceeds available capacity, consider a supported lower-precision or quantized profile, distributing the model across more GPUs, or choosing a smaller model. Verify that the exact model and runtime version support the precision and parallelism you plan to use.
Rank #2
- 5-in-1 USB-C Hub: Experience comprehensive connectivity featuring a Power Delivery input, two USB-A 2.0 ports, a USB-A 3.0 port, and an HDMI port. (Note: The USB-C power delivery input port is only for connecting an external wall charger to power your laptop and cannot power peripheral devices.)
- 90W Pass-Through Charging: Achieve optimal charging with 90W pass-through power to your laptop, supported by a total input of 100W, with the hub reserving 10W for operational efficiency. (Note: Wall charger not included.)
- Quick Data Transfers: Accelerate your productivity with rapid data transfers using a high-speed 5Gbps USB 3.0 port and two 480Mbps USB 2.0 ports.
- 4K HDMI Display: Enhance your visual experience with a hub capable of delivering 4K resolution at 30Hz in both mirror and extend modes. Please note that this hub is compatible with MacBook (macOS 12 and newer), Windows 10 and 11, ChromeOS, and laptops equipped with DP Alt Mode and Power Delivery. Note: This device is not compatible with Linux.
- What You Get: Anker USB-C Hub (5-in-1, 4K HDMI), welcome guide, 18-month warranty, and our friendly customer service.
If inference runs out of memory after loading
Inference needs memory beyond weights. The KV cache grows with inference demands such as context length and concurrent requests; activations, communication buffers, and CUDA graphs also consume memory. Check the serving stack’s context limit, batching and concurrency, and cache budget before changing hardware.
NVIDIA documents --gpu-memory-utilization for its NIM/vLLM context as a budget for model operations, with a documented default of 0.9. Check the documentation for your particular NIM version before applying the setting; do not assume the flag or default applies to other serving stacks.
Rank #3
- Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
- Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
- Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
- Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
- What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.
If logs show the failure during KV-cache allocation and memory statistics show considerable reserved-but-unallocated memory, fragmentation may be a factor. For the NIM/PyTorch context, NVIDIA documents PYTORCH_ALLOC_CONF=expandable_segments:True as a possible remedy. It is a conditional allocator setting, not a general fix for workloads that exceed physical VRAM.
If training reaches a memory peak
Reduce micro-batch size or sequence length to reduce how much work must be resident at once. If your training loop supports it, gradient accumulation can preserve a larger effective batch while using smaller micro-batches. Check the framework’s loss scaling and optimizer-step behavior when changing accumulation.
Rank #4
- Dual Converters, Infinite Potential：Includes 2× USB C male to USB A female adapters and 2× USB A male to USB C female adapters. Perfect for a wide range of uses—tablets with Bluetooth keyboards, expand USB ports on macbook, and more. Two different converters for all your daily needs
- Next-Level 10Gbps & 3A Charging: No more slow 480Mbps, this usb to usb c adapter has a transfer speed of up to 10Gbps, allowing you to do more transferring in less time. This usb adapter fits both USB A and USB C charger, supporting up to 3A fast charging
- Upgraded Exquisite Craftsmanship: With an aluminum alloy housing and metal connector, the usbc to usb adapter is extremely durable and sturdy. Rigorously tested to withstand more than 10,000 times of plugging and unplugging, ensuring long-lasting performance
- Broad Compatible: The usb c to usb adapter widely supports all USB C/ USB A devices like laptops, tablets, cellphones, car chargers, and phone chargers. Such as compatible with MacBook Pro/Air 2023/2022, Thunderbolt 4/3 Devices,Apple MagSafe Watch 9/8/7/SE/Ultra, iPad Pro 2022/2021, Samsung Galaxy S23/S20/S10, and iPhone 17/16/15 Pro. Plug and play
- Please Note: To reach 10Gbps speed, keep the cable under 3.3 ft. For USB A Male to USB C adapters, try flipping the USB C connector. USB C Male to USB A adapters support bidirectional 10Gbps transfer within 3.3 ft
Activation checkpointing is another option. It keeps fewer intermediate activations in memory and recomputes them during the backward pass, trading additional compute for lower activation memory. PyTorch describes the approach in Current and New Activation Checkpointing Techniques in PyTorch.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.If CUDA graph capture or warmup fails
In NVIDIA NIM, graph capture may need additional memory headroom after model and cache allocations. NVIDIA’s guide recommends lowering --gpu-memory-utilization to leave more memory unreserved or disabling CUDA graphs using the documented NIM option or eager-mode flag. Disabling graphs can reduce inference throughput. These instructions are specific to the NIM runtime; check its version-specific documentation rather than applying NIM flags to a different server or to PyTorch generally.
Best Value
- 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
- Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
- Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
- HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
- What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
What torch.cuda.empty_cache() can—and cannot—do
PyTorch says torch.cuda.empty_cache() “Releases all unoccupied cached memory currently held by the caching allocator so that those can be used in other GPU applications and visible in nvidia-smi.” The function releases inactive cached blocks; it does not increase memory available to PyTorch for active allocations.
Use it when releasing unused cached memory could help another GPU application or make nvidia-smi reporting clearer. To address memory held by your own workload, remove unneeded references and reduce or change the live allocations instead. See PyTorch’s CUDA semantics documentation.
When a GPU with more VRAM makes sense
Consider an upgrade if supported smaller or lower-precision configurations, reduced context or concurrency, and workload tuning still cannot meet your intended use. Match capacity to the full workload: model size and precision matter, but so do GPU distribution, KV cache, and runtime overhead. A model’s estimated weight storage alone is not enough to determine whether it will fit.
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.
