NVIDIA L40S vs AMD Strix Halo 128GB for local LLMs
2 reports on the NVIDIA L40S and 317 on the AMD Strix Halo 128GB
Which is faster for local LLMs?
Nobody has reported the same model at the same quant on both cards yet, so there's no measured head-to-head. Memory bandwidth, which caps how fast a card can write, is 3.4x higher on the NVIDIA L40S (864 GB/s on the NVIDIA L40S, 256 on the AMD Strix Halo 128GB). The estimates below compare them on the models people run most.
NVIDIA L40S
- Memory
- 48GB
- Memory bandwidth
- 864 GB/s
- FP16 compute
- 362.1 TFLOPS
- Reports
- 2
AMD Strix Halo 128GB
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 317
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.
| Model | NVIDIA L40S | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 27B | 17.6 t/sQ8_0 | 3.5 t/sFP16 |
| Qwen3.8 125B · 6B active | 80.1 t/sQ2_K | 12.6 t/sQ6_K |
| Qwen3.6 35B · 3B active | 55.4 t/sQ8_0 | 12.6 t/sFP16 |
| DeepSeek V4 Flash 284B · 13B active | doesn't fit at these settings | 33.5 t/sQ2_K |
| Qwen3.6 27B | 17.6 t/sQ8_0 | 3.5 t/sFP16 |
| Gemma 4 26B · 4B active | 47.5 t/sQ8_0 | 9.5 t/sFP16 |
Change the context, RAM or model in the calculator: NVIDIA L40S · AMD Strix Halo 128GB
Every report on each card, with its source: NVIDIA L40S · AMD Strix Halo 128GB