NVIDIA RTX 2080 Ti 22GB (China-mod)
Chinese third-party modification of the stock RTX 2080 Ti, replacing the 11 GB GDDR6 with 22 GB. The TU102 chip, 352-bit memory bus, and 616 GB/s bandwidth are unchanged — only VRAM density doubles. The community uses these cards in multi-card stacks (8× cards × 22 GB = 176 GB on a single chassis for an under-$3,000 budget). Trade-off: Turing architecture is two generations behind; no FP8 support, no transformer-engine kernels, AWQ-INT4 inference works but expect lower tok/s than a modern card per GB of VRAM.
Affiliate disclosure: as an Amazon Associate and partner of other retailers, we earn from qualifying purchases. The verdict on this page is our editorial opinion; affiliate links never influence what we recommend.
Sub-scores sum to 578 / 1000. Headline = 578 × 0.70 (Estimated-confidence discount) = 405. This is an algorithmic performance-tier score — distinct from, and often lower than, the editorial “Our verdict” below, which weighs value and real-world fit (especially for hardware we haven’t measured yet). How scoring works →
Extrapolated from 616 GB/s bandwidth — 73.9 tok/s estimated. No measured benchmarks yet.
Plain-English: Workable at 32B, comfortable at 14B and below — snappy enough for a coding agent; vision models supported.
Verdicts extrapolated from catalog VRAM + bandwidth + ecosystem flags. Hover any chip for the rationale. Want measured numbers? Submit your own run with runlocalai-bench --submit.
Overview
Chinese third-party modification of the stock RTX 2080 Ti, replacing the 11 GB GDDR6 with 22 GB. The TU102 chip, 352-bit memory bus, and 616 GB/s bandwidth are unchanged — only VRAM density doubles. The community uses these cards in multi-card stacks (8× cards × 22 GB = 176 GB on a single chassis for an under-$3,000 budget). Trade-off: Turing architecture is two generations behind; no FP8 support, no transformer-engine kernels, AWQ-INT4 inference works but expect lower tok/s than a modern card per GB of VRAM. Same caveats as any aftermarket mod: no NVIDIA warranty, sourcing from Taobao requires shipping logistics, kernel maturity for old architectures has thinned over time.
Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.
Specs
| VRAM | 22 GB |
| Power draw (peak) | 250 W |
| Released | 2023 |
| Backends | CUDA Vulkan |
Models that fit
Open-weight models small enough to run on NVIDIA RTX 2080 Ti 22GB (China-mod) with usable context.
Frequently asked
What models can NVIDIA RTX 2080 Ti 22GB (China-mod) run?
Does NVIDIA RTX 2080 Ti 22GB (China-mod) support CUDA?
How much does NVIDIA RTX 2080 Ti 22GB (China-mod) cost?
Where next?
Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify hardware specifications.