llamaperf

AMD FirePro D700 6GB vs AMD RX 6600 XT for local LLMs

1 report on the AMD FirePro D700 6GB and 2 on the AMD RX 6600 XT

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 about the same on both (264 GB/s on the AMD FirePro D700 6GB, 256 on the AMD RX 6600 XT). The estimates below compare them on the models people run most.

AMD FirePro D700 6GB
Memory
6GB
Memory bandwidth
264 GB/s
FP16 compute
3.5 TFLOPS
Reports
1
AMD RX 6600 XT
Memory
8GB
Memory bandwidth
256 GB/s
FP16 compute
21.2 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.

ModelAMD FirePro D700 6GBAMD RX 6600 XT
Qwen3.8 27B1.5 t/sQ6_K, layers on CPU1.6 t/sQ6_K, layers on CPU
Qwen3.8 125B · 6B activedoesn't fit at these settingsdoesn't fit at these settings
DeepSeek V4 Flash 284B · 13B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 35B · 3B active14.4 t/sQ5_K_M, experts in RAM14.3 t/sQ5_K_M, experts in RAM
Qwen3.6 27B1.5 t/sQ6_K, layers on CPU1.6 t/sQ6_K, layers on CPU
Gemma 4 26B · 4B active14.9 t/sQ4_K_S, experts in RAM9.1 t/sQ6_K, experts in RAM

Change the context, RAM or model in the calculator: AMD FirePro D700 6GB · AMD RX 6600 XT

Every report on each card, with its source: AMD FirePro D700 6GB · AMD RX 6600 XT

More comparisons