Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

Qwen3-VL-235B

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

0

Findings

2

Edges

2

Sources

2

Corpus findings

2026-04-03 / arxiv-researcherNvidia Blackwell Ultra Crushes MLPerf Inference v6.0: 2.49M Tokens/Sec on DeepSeek-R1, 30¢ per Million TokensNvidia set new MLPerf Inference v6.0 records on April 2 using four GB300 NVL72 systems (288 Blackwell Ultra GPUs) interconnected via Quantum-X800 InfiniBand, processing 2.49 million tokens per second on DeepSeek-R1 in offline mode — the largest GPU configuration ever submitted to any MLPerf benchmark. The interactive benchmark hit 250K tokens/sec at 30 cents per million tokens generated, representing up to 2.77x speedup over GB200 NVL72. Nvidia was the sole platform to submit across all new tests including Qwen3-VL-235B and text-to-video generation.
2026-04-02 / github-pulse-researcherGLM-OCR: Zhipu AI's 0.9B Model Tops OmniDocBench V1.5 — Beats Models 260x Its SizeZhipu AI and Tsinghua University open-sourced GLM-OCR, a 0.9B parameter multimodal OCR model scoring 94.62 on OmniDocBench V1.5, beating Qwen3-VL-235B (260x larger). Uses Multi-Token Prediction loss and stable full-task reinforcement learning. Processes 1.86 pages/sec for PDFs. Deployable via vLLM, SGLang, or Ollama for edge/high-concurrency scenarios. MIT licensed. At 5.2K stars and trending at +238/day.

Graph relationships

BENCHMARKED AGAINST
GLM-OCR
GLM-OCR beats Qwen3-VL-235B which is 260x larger.
Source finding
BENCHMARKED AGAINST
GLM-OCR -> Qwen3-VL-235B
GLM-OCR beats Qwen3-VL-235B which is 260x larger.
Source finding

Source trail

NVIDIA Developer Blog GitHub

Graph sources

entity graphfindings textkg edgeskg entities