llamaperf

NVIDIA RTX 3090 vs NVIDIA Tesla P100 16GB for local LLMs

271 reports on the NVIDIA RTX 3090 and 17 on the NVIDIA Tesla P100 16GB

Which is faster for local LLMs?

On Qwen3.8 27B at 3-bit, the NVIDIA RTX 3090 has 42.3 generation tokens/s (one run); prompt processing 1127.0 tokens/s (one run); the NVIDIA Tesla P100 16GB has 10.0 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 28% higher on the NVIDIA RTX 3090 (936 GB/s on the NVIDIA RTX 3090, 732 on the NVIDIA Tesla P100 16GB).

NVIDIA RTX 3090
Memory
24GB
Memory bandwidth
936 GB/s
FP16 compute
142 TFLOPS
Reports
271
NVIDIA Tesla P100 16GB
Memory
16GB
Memory bandwidth
732 GB/s
FP16 compute
19 TFLOPS
Reports
17

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 Tesla P100 16GB
Qwen3.8 27B3-bit42.3one runPP 1127.0 (one run)llama.cpp16K context10.0one runengine not statedcontext 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 3090NVIDIA Tesla P100 16GB
Qwen3.8 27B33.9 t/sQ4_K_M47.7 t/sQ2_K
Qwen3.8 125B · 6B active19.4 t/sQ2_K, experts in RAMdoesn't fit at these settings
Qwen3.6 35B · 3B active120.1 t/sQ4_K_S157.9 t/sQ2_K
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_M47.7 t/sQ2_K
Gemma 4 26B · 4B active76.4 t/sQ5_K_S106.4 t/sQ3_K_S

Change the context, RAM or model in the calculator: NVIDIA RTX 3090 · NVIDIA Tesla P100 16GB

Every report on each card, with its source: NVIDIA RTX 3090 · NVIDIA Tesla P100 16GB

More comparisons