llamaperf

AMD RX 6700 XT vs AMD RX 9070 XT 16GB for local LLMs

5 reports on the AMD RX 6700 XT and 27 on the AMD RX 9070 XT 16GB

Which is faster for local LLMs?

On Qwen3 8B at 4-bit, the AMD RX 6700 XT has 61.0 generation tokens/s (one run); prompt processing 851.0 tokens/s (one run); the AMD RX 9070 XT 16GB has 98.8 generation tokens/s (one run); prompt processing 4245.0 tokens/s (one run). Those are community reports whose engines and settings differ, so the gap is a rough sign, not a controlled measure of the two cards. Memory bandwidth, which caps how fast a card can write, is 1.7x higher on the AMD RX 9070 XT 16GB (384 GB/s on the AMD RX 6700 XT, 640 on the AMD RX 9070 XT 16GB).

AMD RX 6700 XT
Memory
12GB
Memory bandwidth
384 GB/s
FP16 compute
26.4 TFLOPS
Reports
5
AMD RX 9070 XT 16GB
Memory
16GB
Memory bandwidth
640 GB/s
FP16 compute
195 TFLOPS
Reports
27

Measured on both

Generation and prompt processing speeds from plain runs (one device, one request, no speculative decoding, the whole model in the device's memory) of the same model size at the same bit class. Each side shows the engines and reported context behind its median. Context can mean a configured window or prompt depth, so these are community comparisons with differing settings. How to read these

ModelAMD RX 6700 XTAMD RX 9070 XT 16GB
Qwen3 8B4-bit61.0one runPP 851.0 (one run)llama.cppcontext not stated98.8one runPP 4245.0 (one run)llama.cpp512 context

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. Where a model was also measured above, the measurement wins.

ModelAMD RX 6700 XTAMD RX 9070 XT 16GB
Qwen3 8B60.3 t/sQ3_K_M54.2 t/sQ6_K
Qwen3.8 27B1.6 t/sQ8_0, layers on CPU41.7 t/sQ2_K
Qwen3.8 125B · 6B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 35B · 3B active13.3 t/sQ6_K, experts in RAM138.0 t/sQ2_K
DeepSeek V4 Flash 284B · 13B activedoesn't fit at these settingsdoesn't fit at these settings
DeepSeek V4.1 Flash 552B · 16B activedoesn't fit at these settingsdoesn't fit at these settings
Qwen3.6 27B1.6 t/sQ8_0, layers on CPU41.7 t/sQ2_K

Change the context, RAM or model in the calculator: AMD RX 6700 XT · AMD RX 9070 XT 16GB

Every report on each card, with its source: AMD RX 6700 XT · AMD RX 9070 XT 16GB

More comparisons