llamaperf

Intel Arc Pro B70 vs AMD RX 7900 XTX for local LLMs

26 reports on the Intel Arc Pro B70 and 64 on the AMD RX 7900 XTX

Which is faster for local LLMs?

On Qwen3.8 27B at 4-bit, the Intel Arc Pro B70 has 25.6 generation tokens/s (one run); prompt processing 512.1 tokens/s (one run); the AMD RX 7900 XTX has 40.0 generation tokens/s (7 runs); prompt processing 640.0 tokens/s (4 runs). 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 1.6x higher on the AMD RX 7900 XTX (608 GB/s on the Intel Arc Pro B70, 960 on the AMD RX 7900 XTX). Across 2 shared models with generation measurements on both cards, the Intel Arc Pro B70's median is higher on 0 and the AMD RX 7900 XTX's on 2.

Intel Arc Pro B70
Memory
32GB
Memory bandwidth
608 GB/s
FP16 compute
183.5 TFLOPS
Reports
26
AMD RX 7900 XTX
Memory
24GB
Memory bandwidth
960 GB/s
FP16 compute
123 TFLOPS
Reports
64

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

ModelIntel Arc Pro B70AMD RX 7900 XTX
Qwen3.8 27B4-bit25.6one runPP 512.1 (one run)llama.cppcontext not stated40.07 runsPP 640.0 (4 runs)llama.cpp, Ollama, 2 not stated32K to 220K context, 3 not stated
Qwen3.6 35B · 3B active4-bit63.75 runsPP 977.4 (4 runs)llama.cpp127K to 256K context, 2 not stated125.5one runPP 1874.7 (one run)llama.cppcontext not stated

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.

ModelIntel Arc Pro B70AMD RX 7900 XTX
Qwen3.8 27B15.2 t/sQ6_K34.8 t/sQ4_K_M
Qwen3.6 35B · 3B active55.3 t/sQ5_K_M123.2 t/sQ4_K_S
Qwen3.8 125B · 6B active18.6 t/sQ2_K, experts in RAM19.5 t/sQ2_K, experts in RAM
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 27B15.2 t/sQ6_K34.8 t/sQ4_K_M
Gemma 4 26B · 4B active38.8 t/sQ6_K78.4 t/sQ5_K_S
GLM-5.3 320B · 18B activedoesn't fit at these settingsdoesn't fit at these settings

Change the context, RAM or model in the calculator: Intel Arc Pro B70 · AMD RX 7900 XTX

Every report on each card, with its source: Intel Arc Pro B70 · AMD RX 7900 XTX

More comparisons