AMD Strix Halo 128GB vs NVIDIA T1000 8GB for local LLMs
313 reports on the AMD Strix Halo 128GB and 2 on the NVIDIA T1000 8GB
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 1.6x higher on the AMD Strix Halo 128GB (256 GB/s on the AMD Strix Halo 128GB, 160 on the NVIDIA T1000 8GB). The estimates below compare them on the models people run most.
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 313
- Memory
- 8GB
- Memory bandwidth
- 160 GB/s
- FP16 compute
- 5 TFLOPS
- Reports
- 2
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 T1000 8GB |
|---|---|---|
| Qwen3.8 27B | 3.5 t/sFP16 | 1.3 t/sQ6_K, layers on CPU |
| 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 | 12.4 t/sQ5_K_M, experts in RAM |
| DeepSeek V4 Flash 284B · 13B active | 33.5 t/sQ2_K | doesn't fit at these settings |
| Qwen3.6 27B | 3.5 t/sFP16 | 1.3 t/sQ6_K, layers on CPU |
| Gemma 4 26B · 4B active | 9.5 t/sFP16 | 7.8 t/sQ6_K, experts in RAM |
Change the context, RAM or model in the calculator: AMD Strix Halo 128GB · NVIDIA T1000 8GB
Every report on each card, with its source: AMD Strix Halo 128GB · NVIDIA T1000 8GB