PulseAugur
EN
LIVE 07:05:59

Inception Labs launches Mercury 3 diffusion LLM at 1,068 tokens/sec · 2 sources tracked

By PulseAugur Editorial · [2 sources] ·

Inception Labs has launched Mercury 3, a diffusion-based LLM that achieves 1,068 tokens per second on NVIDIA GPUs, significantly outperforming autoregressive models in speed. This new architecture allows for parallel refinement of tokens across the entire sequence, enabling faster processing for tasks like infilling, editing, and constrained generation. While vendor benchmarks claim parity with models like GPT-6 Luna and Claude Haiku 5.5 in quality, independent evaluations are pending, and the ecosystem for diffusion LLMs is still developing. AI

IMPACT Accelerates agent task completion by reducing model inference time, potentially enabling new real-time AI applications.

RANK_REASON Frontier-lab model release with system card and performance claims. [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Inception Labs launches Mercury 3 diffusion LLM at 1,068 tokens/sec · 2 sources tracked

How we ranked this

Signal score
1 / 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 and performance claims. [lever_c_demoted from frontier_release: ic=2 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
3 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. dev.to — LLM tag TIER_1 English(EN) · Shivam Kumar ·

    Mercury 3 Does 1,068 Tokens/Second With a Diffusion LLM — Here's the Architecture Trick (and How to Try It)

    <p>Today Inception Labs dropped <strong>Mercury 3</strong>: a diffusion-based LLM with a 1M-token context window doing <strong>1,068 tokens/sec on NVIDIA GPUs</strong>, claiming to beat GPT-6 Luna and Claude Haiku 5.5 on benchmarks — at $0.20/$0.70 per million tokens, half price …

  2. dev.to — LLM tag TIER_1 English(EN) · M.T.Ramkrushna ·

    Mercury 3 and the Diffusion LLM Bet: What 1,000 Tokens per Second Changes for Agents (and What It Doesn't)

    <p>Every step of an AI agent waits on the model.</p> <p>Plan, call a tool, read the result, decide, call another tool. If each model call takes a few seconds, a ten-step task feels like forever, and a voice agent feels broken. Most "make it faster" work today is squeezing the sam…

RELATED ENTITIES

RELATED TOPICS