PulseAugur
EN
LIVE 04:23:29

Zhipu AI tests GLM-5.3 model at 490 tokens/sec

By PulseAugur Editorial · [1 sources] ·

Zhipu AI is testing an accelerated version of its GLM-5.3 large language model, reportedly achieving speeds of approximately 490 tokens per second. This new "Highspeed" variant is more than twice as fast as the previous "FlashX" variant, which processed around 200 tokens per second. The faster model is currently being distributed to a select group of ZCode subscribers. AI

IMPACT This speed increase could significantly enhance real-time AI applications and user interaction with Zhipu's models.

RANK_REASON Frontier-lab model release with system card [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Zhipu AI tests GLM-5.3 model at 490 tokens/sec

How we ranked this

Signal score
10 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Frontier-lab model release with system card [lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Zhipu is testing a faster version of its GLM-5.3 model, with users reporting roughly 490 tokens per second - more than double the 200 tokens/s of the FlashX var

    Zhipu is testing a faster version of its GLM-5.3 model, with users reporting roughly 490 tokens per second - more than double the 200 tokens/s of the FlashX variant. The Highspeed variant is being rolled out to randomly selected ZCode subscribers. https:// pandaily.com/zhipu-glm-…

    LINKS pandaily.com/zhipu-glm-5-3-highspeed-zcod…

RELATED ENTITIES

RELATED TOPICS