llamaperf

NVIDIA RTX 3090 vs NVIDIA RTX 5090 Laptop 24GB for local LLMs

271 reports on the NVIDIA RTX 3090 and 11 on the NVIDIA RTX 5090 Laptop 24GB

Which is faster for local LLMs?

On Qwen3.8 27B at 4-bit, the NVIDIA RTX 3090 has 38.4 generation tokens/s (7 runs); prompt processing 561.0 tokens/s (2 runs); the NVIDIA RTX 5090 Laptop 24GB has 33.5 generation tokens/s (2 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 about the same on both (936 GB/s on the NVIDIA RTX 3090, 896 on the NVIDIA RTX 5090 Laptop 24GB).

NVIDIA RTX 3090
Memory
24GB
Memory bandwidth
936 GB/s
FP16 compute
142 TFLOPS
Reports
271
NVIDIA RTX 5090 Laptop 24GB
Memory
24GB
Memory bandwidth
896 GB/s
FP16 compute
200 TFLOPS
Reports
11

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 3090NVIDIA RTX 5090 Laptop 24GB
Qwen3.8 27B4-bit38.47 runsPP 561.0 (2 runs)llama.cpp, vLLM +1, 1 not stated128K to 256K context, 2 not stated33.52 runsllama.cpp, 1 not stated64K to 100K 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 3090NVIDIA RTX 5090 Laptop 24GB
Qwen3.8 27B33.9 t/sQ4_K_M32.4 t/sQ4_K_M
Qwen3.8 125B · 6B active19.4 t/sQ2_K, experts in RAM19.4 t/sQ2_K, experts in RAM
Qwen3.6 35B · 3B active120.1 t/sQ4_K_S115.0 t/sQ4_K_S
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 27B33.9 t/sQ4_K_M32.4 t/sQ4_K_M
Gemma 4 26B · 4B active76.4 t/sQ5_K_S73.2 t/sQ5_K_S

Change the context, RAM or model in the calculator: NVIDIA RTX 3090 · NVIDIA RTX 5090 Laptop 24GB

Every report on each card, with its source: NVIDIA RTX 3090 · NVIDIA RTX 5090 Laptop 24GB

More comparisons