Latest News

ByteShape Squeezes Qwen3.8-27B Into 8.8 GB Hitting 176 Tokens per Second

AlphaSignalGpus

5 hrs ago

Mitsuba Squeezes a 27B Vision Model Into 7.3 GB on One GPU

AlphaSignalLlms

8 hrs ago

China Telecom's Xing4.0 Runs a 29B Coding Agent on 19GB Locally

AlphaSignalLlms

11 hrs ago

FlashML Runs MiniMax H3 Video AI on 8 GB Consumer GPUs

AlphaSignalVideo

15 hrs ago

Aleph Alpha Releases Kolibri-1, an Open German Reasoning Model With 1M-Token Context

AlphaSignalLlms

20 hrs ago

Red Hat Shrinks Nemotron 3.5 Lightning's 30B Agent Model by Half With FP8

AlphaSignalLlms

23 hrs ago

Cohere's North Small Translate Beats DeepL Across 50 Languages With Downloadable Weights

CoherePost Training

1 day ago

OpenBMB's MiniCPM5-2B Gets a 324M Draft Model That Accepts 6 Tokens at Once

AlphaSignalLlms

1 day ago

Microsoft's DeBERTa-v3-small Beats RoBERTa Using Half the Parameters

AlphaSignalLlms

1 day ago

Open-Source VieNeu-TTS v3 Turbo Runs 48 kHz Vietnamese Speech on CPUs

AlphaSignalAudio

1 day ago

livenerf Catches Claude Opus 5.5 Drifting With a Daily 78-Question Trap

AlphaSignalBenchmarks

1 day ago

Ideogram 4.5 Fights Edit Drift With 27x Pricing Spread and Multi-Turn Precision

Artificial AnalysisImage

1 day ago