Calculator GPUs Engines Guides Blog MCP Advertise

Sponsored

Give your agent the live web in one calltrawlia.coTry Trawlia →

llamaperf/Intel Arc Pro B70/report

Qwen2.5

on Intel Arc Pro B70 · llama.cpp

Aug 28, 2026

Throughput

63.0 t/s gen

Sponsoredllamaperf.com

Advertise on llamaperf

Put your product in front of people choosing GPUs and models to run locally. One flat price per week, every ad slot on the site.

See the offer →

View source ↗

Browse

All GPUs
All models
All engines
Calculator
Compare GPUs
Leaderboard
Best
Best for coding
Macs
Guides
Blog
Trending MCP servers
Local model performance
Discussions

Best of

GPUs for running local LLMs
Mac for running local LLMs
NVIDIA GPUs for local LLMs
GPUs for 70B and larger local LLMs
GPUs for 30B local LLMs
Mac for 70B and larger local LLMs

Popular GPUs

AMD Strix Halo 128GB
NVIDIA RTX 3090
NVIDIA RTX 5090
NVIDIA DGX Spark
M5 Max 48GB
NVIDIA RTX Pro 6000 Blackwell
NVIDIA RTX 5060 Ti 16GB
NVIDIA RTX 3060 12GB

Popular models

Qwen3.8
Qwen3.6
DeepSeek V4 Flash
Gemma 4
Qwen3.5
Qwen3
GLM-5.3
gpt-oss

Engines

llama.cpp
vLLM
MLX
Strata
Ollama
oMLX

llamaperf · community-sourced local model performance reports

Submit a report Advertise About Contact Privacy