llamaperf

NVIDIA RTX 2080 Ti 22GB (modded) vs AMD Strix Halo 128GB for local LLMs

11 reports on the NVIDIA RTX 2080 Ti 22GB (modded) and 348 on the AMD Strix Halo 128GB

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 AMD Strix Halo 128GB has 60.0 generation tokens/s (7 runs); prompt processing 1005.3 tokens/s (7 runs). 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 2.4x higher on the NVIDIA RTX 2080 Ti 22GB (modded) (616 GB/s on the NVIDIA RTX 2080 Ti 22GB (modded), 256 on the AMD Strix Halo 128GB).

NVIDIA RTX 2080 Ti 22GB (modded)
Memory
22GB
Memory bandwidth
616 GB/s
FP16 compute
108 TFLOPS
Reports
11
AMD Strix Halo 128GB
Memory
128GB unified
Memory bandwidth
256 GB/s
FP16 compute
59 TFLOPS
Reports
348

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)AMD Strix Halo 128GB
Qwen3.6 35B · 3B active4-bit69.0one runllama.cpp16K context60.07 runsPP 1005.3 (7 runs)llama.cpp, 3 not stated30K context, 6 not stated

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)AMD Strix Halo 128GB
Qwen3.6 35B · 3B active93.6 t/sQ3_K_M12.6 t/sFP16
Qwen3.8 27B25.1 t/sQ4_K_S3.5 t/sFP16
Qwen3.8 125B · 6B active18.6 t/sQ2_K, experts in RAM12.6 t/sQ6_K
DeepSeek V4 Flash 284B · 13B activedoesn't fit at these settings33.5 t/sQ2_K
DeepSeek V4.1 Flash 552B · 16B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 27B25.1 t/sQ4_K_S3.5 t/sFP16
Gemma 4 26B · 4B active56.6 t/sQ4_K_M9.5 t/sFP16

Change the context, RAM or model in the calculator: NVIDIA RTX 2080 Ti 22GB (modded) · AMD Strix Halo 128GB

Every report on each card, with its source: NVIDIA RTX 2080 Ti 22GB (modded) · AMD Strix Halo 128GB

More comparisons