PulseAugur
EN
LIVE 07:09:28

Qwen3.8-Flash-Next hits 685 tokens/sec on NVIDIA GPUs

By PulseAugur Editorial · [1 sources] ·

Lightseekorg has achieved a new benchmark for the Qwen3.8-Flash-Next model, reaching 685 output tokens per second per user on NVIDIA GB300 GPUs with NVFP4. This result highlights the model's inference potential and the optimizations achieved in its kernel and serving infrastructure. Alibaba's Qwen team congratulated Lightseekorg on their impressive TokenSpeed results, encouraging further exploration of the model's capabilities. AI

IMPACT Demonstrates significant inference speed improvements for Qwen models, potentially impacting deployment costs and real-time application performance.

RANK_REASON Benchmark result for an existing model, not a new release. [lever_c_demoted from research: ic=1 ai=1.0]

Read on X — Qwen (Alibaba) →

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

Qwen3.8-Flash-Next hits 685 tokens/sec on NVIDIA GPUs

How we ranked this

Signal score
6 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Benchmark result for an existing model, not a new release. [lever_c_demoted from research: 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, 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 [1]

  1. X — Qwen (Alibaba) TIER_1 English(EN) · Alibaba_Qwen ·

    Congrats to @lightseekorg on the impressive TokenSpeed results! 🚀 Great to see Qwen3.8-Flash-Next reaching 685 output tokens/s per user on Nvida GPUs. Excited t

    Congrats to @lightseekorg on the impressive TokenSpeed results! 🚀 Great to see Qwen3.8-Flash-Next reaching 685 output tokens/s per user on Nvida GPUs. Excited to see the community unlock more of Qwen’s inference potential!

RELATED ENTITIES

RELATED TOPICS