YuE2-3B on RTX 5060 Ti
Yes — YuE2-3B runs on the RTX 5060 Ti (16 GB). Fastest community-measured result: 205.23 s.
YuE2-3B on RTX 5060 Ti: 16GB measured, worst case included
| Task | Quant | Speed | VRAM | Works | Confidence | Source | Verified |
|---|---|---|---|---|---|---|---|
| t2m | bf16 | 205.23s | ✓ | huggingface.co· first-party measurement | 2026-09-14 |
- t2mbf16205.23 s
Vendor runtime yue2_infer 0.1.5 (m-a-p/YuE2-3B @1a96eca6), cot="full", default budget: a 201.04 s song generated in 205.23 s. cot="off": 165.40 s of audio in 144.39 s. KV filled to the full 24,576-token context: 299.96 s in 315.53 s (cot full); 345.68 s in 298.55 s with cot off and the second CFG branch, the worst case the library allows. Whole-card peaks 10,291 / 10,516 / 11,786 / 13,804 MiB of 16,311, all under the library's own total minus 2 GiB clamp; no OOM. Each run a separate process, cold. WSL2 on Windows 11, torch 2.10.0+cu128, driver 591.86, NVML at 20 Hz, display attached. Unreplicated: one rig, one operator.
recorded from huggingface.co ↗ · verified 2026-09-14
- musicintermediate16GB+
YuE2-3B on RTX 4060 Ti 16GB: the fit transfers, the timings do not
- musicintermediate16GB+
YuE2-3B on RTX 4070 Ti Super: the 16GB fit is arithmetic, not luck
- musicintermediate16GB+
YuE2-3B on RTX 4080 Super: full-length songs inside the 16GB clamp
- musicintermediate16GB+
YuE2-3B on RTX 4080: the measured 16GB fit, carried across to Ada
Can you run YuE2-3B on RTX 5060 Ti?
Yes — YuE2-3B runs on the RTX 5060 Ti (16 GB). Fastest community-measured result: 205.23 s.
Which quantizations have been tested for YuE2-3B on RTX 5060 Ti?
bf16 — measured in community benchmarks.
How fast is YuE2-3B on RTX 5060 Ti?
Up to 205.23 s (t2m), the fastest community-measured result.
Are there step-by-step instructions for YuE2-3B on RTX 5060 Ti?
Yes — a step-by-step recipe documents YuE2-3B on the RTX 5060 Ti, linked at the top of this page.