llamaperf

AMD Radeon 780M vs NVIDIA RTX 5090 for local LLMs

8 reports on the AMD Radeon 780M and 197 on the NVIDIA RTX 5090

Which is faster for local LLMs?

On Gemma 4 26B · 4B active at 4-bit, the AMD Radeon 780M has 25.0 generation tokens/s (one run); prompt processing 208.7 tokens/s (one run); the NVIDIA RTX 5090 has 243.9 generation tokens/s (one run); prompt processing 13809.2 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 14.9x higher on the NVIDIA RTX 5090 (120 GB/s on the AMD Radeon 780M, 1,792 on the NVIDIA RTX 5090).

AMD Radeon 780M
Memory
shared memory unified
Memory bandwidth
not on record
FP16 compute
not on record
Reports
8
NVIDIA RTX 5090
Memory
32GB
Memory bandwidth
1,792 GB/s
FP16 compute
419 TFLOPS
Reports
197

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

ModelAMD Radeon 780MNVIDIA RTX 5090
Gemma 4 26B · 4B active4-bit25.0one runPP 208.7 (one run)llama.cppcontext not stated243.9one runPP 13809.2 (one run)llama.cppcontext 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.

ModelAMD Radeon 780MNVIDIA RTX 5090
Gemma 4 26B · 4B activenot in the calculator yet114.5 t/sQ6_K
Qwen3.8 27Bnot in the calculator yet44.9 t/sQ6_K
Qwen3.8 125B · 6B activenot in the calculator yet20.3 t/sQ2_K, experts in RAM
Qwen3.6 35B · 3B activenot in the calculator yet163.0 t/sQ5_K_M
DeepSeek V4 Flash 284B · 13B activenot in the calculator yetdoesn't fit at these settings
DeepSeek V4.1 Flash 552B · 16B activenot in the calculator yetdoesn't fit at these settings
Qwen3.6 27Bnot in the calculator yet44.9 t/sQ6_K

Change the context, RAM or model in the calculator: AMD Radeon 780M · NVIDIA RTX 5090

Every report on each card, with its source: AMD Radeon 780M · NVIDIA RTX 5090

More comparisons