llamaperf

NVIDIA RTX 2080 Ti 22GB (modded) vs NVIDIA RTX 3090 for local LLMs

11 reports on the NVIDIA RTX 2080 Ti 22GB (modded) and 271 on the NVIDIA RTX 3090

Which is faster for local LLMs?

On Qwen3.6 35B · 3B active at 4-bit, the NVIDIA RTX 2080 Ti 22GB (modded) has 69.0 generation tokens/s (one run); the NVIDIA RTX 3090 has 101.7 generation tokens/s (one run). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 1.5x higher on the NVIDIA RTX 3090 (616 GB/s on the NVIDIA RTX 2080 Ti 22GB (modded), 936 on the NVIDIA RTX 3090).

NVIDIA RTX 2080 Ti 22GB (modded)
Memory
22GB
Memory bandwidth
616 GB/s
FP16 compute
108 TFLOPS
Reports
11
NVIDIA RTX 3090
Memory
24GB
Memory bandwidth
936 GB/s
FP16 compute
142 TFLOPS
Reports
271

Measured on both

Generation and prompt processing speeds from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same bit class. Each side shows the engines and reported context behind its median. Context can mean a configured window or prompt depth, so these are community comparisons with differing settings. How to read these

ModelNVIDIA RTX 2080 Ti 22GB (modded)NVIDIA RTX 3090
Qwen3.6 35B · 3B active4-bit69.0one runllama.cpp16K context101.7one runllama.cpp64K context

Estimated by the calculator

The quant the calculator recommends for each card and its estimated speed at a 32,768-token context with 32 GB of system RAM, from memory bandwidth and the model's shape. Where a model was also measured above, the measurement wins.

ModelNVIDIA RTX 2080 Ti 22GB (modded)NVIDIA RTX 3090
Qwen3.6 35B · 3B active93.6 t/sQ3_K_M120.1 t/sQ4_K_S
Qwen3.8 27B25.1 t/sQ4_K_S33.9 t/sQ4_K_M
Qwen3.8 125B · 6B active18.6 t/sQ2_K, experts in RAM19.4 t/sQ2_K, experts in RAM
DeepSeek V4 Flash 284B · 13B activedoesn't fit at these settingsdoesn't fit at these settings
DeepSeek V4.1 Flash 552B · 16B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 27B25.1 t/sQ4_K_S33.9 t/sQ4_K_M
Gemma 4 26B · 4B active56.6 t/sQ4_K_M76.4 t/sQ5_K_S

Change the context, RAM or model in the calculator: NVIDIA RTX 2080 Ti 22GB (modded) · NVIDIA RTX 3090

Every report on each card, with its source: NVIDIA RTX 2080 Ti 22GB (modded) · NVIDIA RTX 3090

More comparisons