NVIDIA RTX 4090 vs NVIDIA RTX 5060 Ti 16GB for local LLMs
62 reports on the NVIDIA RTX 4090 and 72 on the NVIDIA RTX 5060 Ti 16GB
Which is faster for local LLMs?
On Gemma 4 26B · 4B active at 4-bit, the NVIDIA RTX 4090 has 149.6 generation tokens/s (one run); the NVIDIA RTX 5060 Ti 16GB has 95.2 generation tokens/s (one run); prompt processing 3476.0 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 2.3x higher on the NVIDIA RTX 4090 (1,008 GB/s on the NVIDIA RTX 4090, 448 on the NVIDIA RTX 5060 Ti 16GB). Across 3 shared models with generation measurements on both cards, the NVIDIA RTX 4090's median is higher on 3 and the NVIDIA RTX 5060 Ti 16GB's on 0.
- Memory
- 24GB
- Memory bandwidth
- 1,008 GB/s
- FP16 compute
- 330 TFLOPS
- Reports
- 62
- Memory
- 16GB
- Memory bandwidth
- 448 GB/s
- FP16 compute
- 95 TFLOPS
- Reports
- 72
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
| Model | NVIDIA RTX 4090 | NVIDIA RTX 5060 Ti 16GB |
|---|---|---|
| Gemma 4 26B · 4B active4-bit | 149.6one runOllamacontext not stated | 95.2one runPP 3476.0 (one run)llama.cpp64K context |
| Qwen2.5 7B4-bit | 158.9one runllama.cppcontext not stated | 77.0one runllama.cppcontext not stated |
| Qwen3.6 27B4-bit | 25.0one runLM Studio120K context | 22.0one runPP 760.0 (one run)llama.cpp75K 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.
| Model | NVIDIA RTX 4090 | NVIDIA RTX 5060 Ti 16GB |
|---|---|---|
| Gemma 4 26B · 4B active | 82.3 t/sQ5_K_S | 65.1 t/sQ3_K_S |
| Qwen2.5 7B | 79.2 t/sQ8_0 | 35.2 t/sQ8_0 |
| Qwen3.6 27B | 36.5 t/sQ4_K_M | 29.2 t/sQ2_K |
| Qwen3.8 27B | 36.5 t/sQ4_K_M | 29.2 t/sQ2_K |
| Qwen3.8 125B · 6B active | 19.6 t/sQ2_K, experts in RAM | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 129.3 t/sQ4_K_S | 96.6 t/sQ2_K |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | doesn't fit at these settings |
| DeepSeek V4.1 Flash 552B · 16B active | doesn't fit at these settings | doesn't fit at these settings |
| GLM-5.3 320B · 18B active | doesn't fit at these settings | doesn't fit at these settings |
Change the context, RAM or model in the calculator: NVIDIA RTX 4090 · NVIDIA RTX 5060 Ti 16GB
Every report on each card, with its source: NVIDIA RTX 4090 · NVIDIA RTX 5060 Ti 16GB