AMD Instinct MI300A vs AMD Strix Halo 128GB for local LLMs
0 reports on the AMD Instinct MI300A and 82 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 20.7x higher on the AMD Instinct MI300A (5,300 GB/s on the AMD Instinct MI300A, 256 on the AMD Strix Halo 128GB). The estimates below compare them on the models people run most.
- Memory
- 128GB unified
- Memory bandwidth
- 5,300 GB/s
- FP16 compute
- 980.6 TFLOPS
- Reports
- 0
- Memory
- 128GB unified
- Memory bandwidth
- 256 GB/s
- FP16 compute
- 59 TFLOPS
- Reports
- 82
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 Instinct MI300A | AMD Strix Halo 128GB |
|---|---|---|
| Qwen3.8 27B | 54.0 t/sFP16 | 3.5 t/sFP16 |
| Qwen3.8 125B · 6B active | 193.8 t/sQ6_K | 12.6 t/sQ6_K |
| DeepSeek V4 Flash 284B · 13B active | 514.6 t/sQ2_K | 33.5 t/sQ2_K |
| Qwen3.6 35B · 3B active | 194.3 t/sFP16 | 12.6 t/sFP16 |
| Qwen3.6 27B | 54.0 t/sFP16 | 3.5 t/sFP16 |
| Gemma 4 26B · 4B active | 145.8 t/sFP16 | 9.5 t/sFP16 |
Change the context, RAM or model in the calculator: AMD Instinct MI300A · AMD Strix Halo 128GB
Every report on each card, with its source: AMD Instinct MI300A · AMD Strix Halo 128GB