1. X
  2. TNG Technology Consulting GmbH
Log inSign up
TNG Technology Consulting GmbH
1,693 posts
Image
user avatar
TNG Technology Consulting GmbH
@tngtech
TNG, aka "The Nerd Group", is a consulting partnership focused on high end information technology, particularly AI. 933 employees, 99.9% academics, ~53% PhDs.
Unterföhring, Deutschland
tngtech.com/en
Joined December 2010
176
Following
2,217
Followers
RepliesRepliesArticlesArticlesMediaMedia
  • Pinned
    user avatar
    TNG Technology Consulting GmbH
    @tngtech
    Jul 2, 2025
    Today we release DeepSeek-TNG R1T2 Chimera. This new Chimera is a Tri-Mind Assembly-of-Experts model with three parents, namely R1-0528, R1 and V3-0324. R1T2 operates at a sweet spot in intelligence vs. output token length. It appears to be... * about 20% faster than R1, and
    R1T2-Chimera: Intelligence Score vs. Inference Cost
    128K
  • user avatar
    TNG Technology Consulting GmbH
    @tngtech
    Aug 1
    We calculated okayish, but not the greatest results for @deepseek_ai's V4F-0731 in @sam_paech's new EQ-Bench v4 benchmark. It is an interesting question whether this is a systematic effect of the new post training of 0731: How does heavy RL affect a model's personality, could it
    Image
    1.1K
  • user avatar
    TNG Technology Consulting GmbH
    @tngtech
    Jul 31
    Brain-for-the-buck: In ELOs-per-dollar, @deepseek_ai's V4F-0731 seems almost unbeatable, calculated using @sam_paech's EQ-Bench v3 and @OpenRouter prices. But more than just honorable mentions go to @OpenAI's gpt-5.6-luna, which is better and still price-competitive, which most
    Image
    313
  • user avatar
    TNG Technology Consulting GmbH
    @tngtech
    Jul 31
    We benchmarked the new @deepseek_ai V4 Flash 0731 with our TL;DR-bench via @OpenRouter. The model scores very well for its model size. In our benchmarks, it's significantly stronger than the older DeepSeek V4 Flash version that we have deployed, and comparable to GLM 5.2 with
    Image
    473
  • user avatar
    TNG Technology Consulting GmbH
    @tngtech
    Jul 30
    Today 11:05: 283,717 GLM-5.2 FP8 input tokens per second on our internal cluster, its best so far. Naively extrapolating, the speed corresponds to 24.5Bt/d. Note to self: We need more GPUs. And 谢谢 / thanks to @Zai_org, you guys are always invited here to Munich.
    Image
    330
  • See @tngtech's full profile

    Sign up
    Log in

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Advertisement
Advertisement