PulseAugur
EN
LIVE 19:11:59

Cerebras offers Qwen 3.8 27B model at 1500 tokens/sec

By PulseAugur Editorial · [4 sources] ·

Cerebras has announced the availability of the Qwen 3.8 27B model on its platform, capable of processing at 1500 tokens per second. The company emphasizes that it serves original, unpruned versions of open-source models through its public endpoints. While Cerebras researches pruning techniques like REAP, these modified models are shared separately with the research community on Hugging Face and are not part of the production API. AI

IMPACT Provides access to a specific LLM on specialized hardware, potentially improving inference speeds for certain applications.

RANK_REASON Availability of an open-source model on a specific hardware platform.

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 4 sources. How we write summaries →

Cerebras offers Qwen 3.8 27B model at 1500 tokens/sec

How we ranked this

Signal score
48 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Availability of an open-source model on a specific hardware platform.
Source corroboration
4 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
model release, infra
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 [4]

  1. Hacker News — AI stories ≥50 points TIER_1 English(EN) · altertable ·

    Qwen 3.8 27B available on Cerebras at 1500 tok/SEC

  2. Mastodon — mastodon.social TIER_1 English(EN) · h4ckernews ·

    Qwen 3.8 27B available on Cerebras at 1500 tok/SEC https:// inference-docs.cerebras.ai/mod els/overview Comments: https:// news.ycombinator.com/item?id=4 955452

    Qwen 3.8 27B available on Cerebras at 1500 tok/SEC https:// inference-docs.cerebras.ai/mod els/overview Comments: https:// news.ycombinator.com/item?id=4 9554520 # HackerNews # Qwen3 .8 # Cerebras # AI # Model # 1500tok # SEC # MachineLearning

    LINKS inference-docs.cerebras.ai/…/overview
  3. Mastodon — mastodon.social TIER_1 English(EN) · CuratedHackerNews ·

    Qwen 3.8 27B available on Cerebras at 1500 tok/SEC https:// inference-docs.cerebras.ai/mod els/overview # ai

    Qwen 3.8 27B available on Cerebras at 1500 tok/SEC https:// inference-docs.cerebras.ai/mod els/overview # ai

    LINKS inference-docs.cerebras.ai/…/overview
  4. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Qwen 3.8 27B available on Cerebras at 1500 tok/SEC https://inference-docs.cerebras.ai/models/overview # HackerNews # Tech # AI

    Qwen 3.8 27B available on Cerebras at 1500 tok/SEC https://inference-docs.cerebras.ai/models/overview # HackerNews # Tech # AI

    LINKS inference-docs.cerebras.ai/…/overview

RELATED ENTITIES

RELATED TOPICS