AMD Strix Halo 128GB vs NVIDIA V100 16GB for local LLMs
318 reports on the AMD Strix Halo 128GB and 16 on the NVIDIA V100 16GB
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 3.5x higher on the NVIDIA V100 16GB (256 GB/s on the AMD Strix Halo 128GB, 900 on the NVIDIA V100 16GB). The estimates below compare them on the models people run most.
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 318
- Memory
- 16GB
- Memory bandwidth
- 900 GB/s
- FP16 compute
- 125 TFLOPS
- Reports
- 16
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 | AMD Strix Halo 128GB | NVIDIA V100 16GB |
|---|---|---|
| Qwen3.8 27B | 3.5 t/sFP16 | 58.7 t/sQ2_K |
| Qwen3.8 125B · 6B active | 12.6 t/sQ6_K | doesn't fit at these settings |
| Qwen3.6 35B · 3B active | 12.6 t/sFP16 | 194.1 t/sQ2_K |
| DeepSeek V4 Flash 284B · 13B active | 33.5 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 27B | 3.5 t/sFP16 | 58.7 t/sQ2_K |
| Gemma 4 26B · 4B active | 9.5 t/sFP16 | 130.8 t/sQ3_K_S |
Change the context, RAM or model in the calculator: AMD Strix Halo 128GB · NVIDIA V100 16GB
Every report on each card, with its source: AMD Strix Halo 128GB · NVIDIA V100 16GB