四张 Intel Arc Pro B70 对一张 RTX PRO 6000，vLLM 跑到 32 并发：
This is a AI post classified by AGK Intelligence as AI infra & evals (a model release), kept by the AI Radar because it carries real work, not commentary.
四张 Intel Arc Pro B70 对一张 RTX PRO 6000，vLLM 跑到 32 并发： 1. Mistral Small 24B，四张 B70 8321 tok/s，比 PRO 6000 多 65% 2. Qwen3 Coder 30B，PRO 6000 8772，B70 6643 3. GPT-OSS-120B，B70 6870，大约是 PRO 6000 的四分之三 并发低的时候反过来。单路四张 B70 是 450 tok/s，到 4 并发为止都是 PRO 6000 领先，B70 到 8 并发才反超。 价格差得多。B70 首发 949 美元一张，四张 3796，现在街价已经过了 1100。我这张 PRO 6000 是 9000 买的。 一个人自己用，并发很少到 8，单卡 96GB 更省心。B70 得四张一起跑，软件栈也还在追，有些量化路径还跑不通。 测试里还有单台 DGX Spark，Mistral 24B 最高 527 tok/s。24B 的稠密模型全靠带宽，Spark 吃亏。
Posted by Wei (7.1k followers) 1 days ago · 1 likes · 381 views · view the original post on X. Kept by the AI Radar as AI infra & evals.
More AI work like this
- Enterprise AI is only as useful as the data and business context behind it. — @databricks
- DecodeWall: another benchmark I'm building, focused on concurrent calls. — @ivanfioravanti
- KindlingAI's GLM 5.3 Flash for one Spark recipe is here! 700k total KV on DGX OS (up to… — @mmastrac
- A small model coaching a giant? Aiona checks the held-out tie and SMF’s memory-card… — @MichaelGannotti
- Ranking inference providers six ways — @AdamHoltererer
- Harness adapters training is now live! — @yb2698
- NVIDIA is giving Kimi K3.1 Pro away for free. — @VaibhavSisinty
- The world’s first co-packaged optics Ethernet switch is in full production. — @NVIDIAAIInfra
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:05 UTC. Full method.