RTX 5060 Ti 16GB
NVIDIAconsumer| Overview | |
|---|---|
| Architecture | Blackwell (2025) |
| Compute capability | 12.0 |
| Memory | |
| VRAM | 16 GB GDDR7 |
| Memory bandwidth | 448 GB/s |
| Compute — vector | |
| FP32 | 23.7 TFLOPS |
| Compute — matrix / tensor | |
| FP4 (MXFP4 / NVFP4) | 379.5 TFLOPS |
| Cores & clocks | |
| Shader cores | 4,608 |
| Peak clock | 2,570 MHz |
| Board & system | |
| TDP | 180 W |
| PCIe | PCIe Gen5 |
Compatible CUDA Toolkit versions
PyTorch on the RTX 5060 Ti 16GB
Check against your driver and Python version →
The newest PyTorch, 2.14.0, runs on this card with a plain pip install torch.
| PyTorch | CUDA builds that run on this card | Plain pip install torch |
|---|---|---|
| 2.14.0 | 13.0, 13.2 | works |
| 2.13.0 | 12.9, 13.0, 13.2 | works |
| 2.12.0 | 13.0, 13.2 | works |
| 2.11.0 | 12.8, 12.9, 13.0 | works |
| 2.10.0 | 12.8, 12.9, 13.0 | works |
| 2.9.0 | 12.8, 12.9, 13.0 | works |
| 2.8.0 | 12.8, 12.9 | works |
| 2.7.0 | 12.8 | doesn't (CUDA 12.6 build) |
| 2.6.0 | none | doesn't (CUDA 12.4 build) |
| 2.5.0 | none | doesn't (CUDA 12.4 build) |
| 2.4.0 | none | doesn't (CUDA 12.1 build) |
| 2.3.0 | none | doesn't (CUDA 12.1 build) |
| 2.2.0 | none | doesn't (CUDA 12.1 build) |
| 2.1.0 | none | doesn't (CUDA 12.1 build) |
| 2.0.0 | none | doesn't (CUDA 11.7 build) |
| 1.13.0 | none | doesn't (CUDA 11.7 build) |
| 1.12.0 | none | — |
| 1.11.0 | none | — |
From each build's compiled architecture list (Linux x86_64 wheels). Your driver must also support the CUDA version — see compatible CUDA versions.
Libraries on the RTX 5060 Ti 16GB
Whether each library's own requirements cover this card. Each row links to the version and source it was checked against on library support.
| Library | Supported | Details |
|---|---|---|
| vLLM 0.30.0 | Yes | |
| FlashAttention-2 2.8.3.post1 | Yes | |
| FlashAttention-3 main (2026-09-27) | No | no build for compute capability 12.0 |
| bitsandbytes 0.50.2 | Yes | |
| TensorRT 11.3.0 | Yes | |
| llama.cpp master (2026-09-27) | Yes |
Native low-precision formats
Whether the card's matrix hardware runs these formats natively. Without native support a format can still work, but through slower emulation or conversion, not at the card's rated speed.
| BF16 | FP8 | FP4 |
|---|---|---|
| Native | Native | Native |
Source: NVIDIA TensorRT 11.3.0 support matrix (hardware precision table).
Added 2026-09-27: the cheapest 16 GB Blackwell card, with native FP4. Sources, all NVIDIA: 4,608 CUDA cores, 2.57 GHz boost, "759 AI TOPS", "16 GB / 8 GB GDDR7", 128-bit and 448 GB/sec from the RTX 50 Series table on NVIDIA's GeForce compare page (nvidia.com/en-us/geforce/graphics-cards/compare/), which also confirms this site's RTX 5090 bandwidth (1,792 GB/sec). 180 W Total Graphics Power from the RTX 5060 family product page. fp32TFLOPS 23.7 is cores × 2 × 2.57 GHz. fp4TFLOPS 379.5 is half the 759 "AI TOPS", which on Blackwell is the FP4 rate with sparsity (the same reading as the RTX 5090 entry's 3,352 / 1,676). No MSRP recorded: not found on an NVIDIA page.