AITOPAI热报
ModelsMulti-sourceSelected

Ant Ling's Ming-3.0 speech models run locally from 0.5B

@atomic_chat_hq@atomic_chat_hq
Post· 5 sources
View the post
Why we picked it

Small-parameter speech models that top open benchmarks change the calculus for on-device voice assistants, cutting cloud costs and latency. Developers building voice apps in low-connectivity markets across Southeast Asia can deploy these locally without API dependence. Compared with larger proprietary speech APIs, the 0.5B starting size makes experimentation cheap on a single GPU or even CPU.

Ant Ling (Ant Group's Ling AGI lab) released Ming-3.0, a set of five open-source speech models that handle speech generation, listening and transcription. The voice model ranks #1 among open models on Artificial Analysis. Model sizes start at just 0.5B parameters, making local deployment on consumer hardware feasible. The models can be run locally via Atomic Chat's tooling.

Original · @atomic_chat_hq

Run @AntLingAGI speech models locally 🎙️

Ming-3.0 is 5 open models that talk, listen and write down what you say

Its voice model now ranks #1 among open models on Artificial Analysis starting at just 0.5B

Run AI models locally -> https://t.co/RbcCOIgVkj https://t.co/vbqafAAd2x

#Ming-3.0#Ant Ling#open-source models#speech recognition#on-device AI

Keep reading

Recent stories with the same tag or section
ModelsBuildersMulti-sourceSelected16:43
Ant Group open-sources 5 Ming-3.0 speech models

The three links are composable and self-deployable, so a team can build a full listen-understand-speak voice agent without paying for proprietary APIs. Deployers in multilingual markets gain a working path for dialect-heavy ASR and instruction-driven TTS in one stack. Compared with closed services like OpenAI's audio APIs, this stack keeps weights local and lets you fine-tune each stage separately.

#Ant Group#Ming-3.0#TTS#ASR
Event
AIGCLINK@aigclink5 sourcesSource
ModelsBuildersMulti-sourceSelected00:31
Ant Ling's Ming-3.0 speech models get day-0 vLLM-Omni support

Day-0 inference support means developers can productionise open speech models immediately instead of waiting on community adapters, cutting integration work for voice pipelines. Teams building ASR, TTS or audio-understanding agents can compare Ming-3.0's MoE sizing against closed APIs and self-host at lower cost. The 0.5B to 126B-A6.5B spread also gives Southeast Asian startups an on-premise option for multilingual voice work.

#Ming-3.0#Ant Ling AGI#vLLM-Omni#speech models
Event
官方账号vLLM@vllm_project5 sourcesSource
ModelsUS vs ChinaMulti-sourceSelected10:07
Anthropic models lead completeness but trail OpenAI on medical benchmarks

Verbose medical answers earn completeness points but introduce more claims that can contradict the record, so length itself becomes an accuracy liability. Teams building clinical documentation or decision-support tools should weight length-adjusted scores over raw ones, since the top model changes depending on that choice. Against alternatives like GPT-6 Astra, Claude models suit use cases where covering every rubric point matters more than brevity.

#Claude Opus 5.5#Claude Sonnet 5.5#GPT-6 Astra#HealthBench
Event
官方账号Artificial Analysis@ArtificialAnlys11 sourcesSource
ModelsBuildersMulti-sourceSelected03:11
Recursive Releases Flint, an Open-Weight 40B Coding Model

An Apache 2.0 license means teams can run, fine-tune and ship Flint commercially without restrictions, a rare setup among coding models. Its 40B MoE design targets local deployment, so developers with a 64GB-class GPU can test it offline and benchmark the 220 tokens-per-second claim themselves. Anyone comparing local coding assistants against proprietary cloud options has a new open baseline to try.

#Recursive#Flint#open-source models#coding assistants
Event
TestingCatalog@testingcatalog7 sourcesSource
ModelsBuildersMulti-sourceSelected00:47
vLLM adds Day-0 support for Recursive's Flint model

A sparse 2.5B-active architecture hitting 500 TPS on one GB200 shows how far inference efficiency now goes without speculative decoding, a benchmark point worth tracking against dense models of similar quality. Teams serving long-context workloads can run Flint in vLLM immediately in either NVFP4 or BF16. Builders evaluating open-weight model serving stacks should compare its throughput on their own GPUs.

#vLLM#Flint#NVFP4#open-source models
Event
官方账号vLLM@vllm_project8 sourcesSource
ModelsBuildersMulti-sourceSelected00:13
Scale AI Post-Trains NVIDIA Nemotron 3.5 Super VL

Post-training a smaller open NVIDIA model to match frontier accuracy at 1/40 the inference cost is a concrete signal that domain-specific fine-tuning can undercut flagship APIs for production agent workloads. Teams running high-volume ticket or support agents should benchmark Nemotron 3.5 Super VL against their current frontier model on cost and latency. The Skydance collaboration shows enterprises bringing their own production data to post-training partners.

#NVIDIA#Nemotron#Scale AI#fine-tuning
Event
官方账号Scale AI@scale_AI11 sourcesSource