Latest

Every published item, in order · 6306 items
Oct 21
ModelsBuildersSelected21:07
MiniCPM-V 4.7 runs 35B MoE on phones at 20.51 tokens/s

Smarter scheduling, not a smaller model, is what makes a 35B-parameter MoE fit and run fast on consumer phones — no retraining required, since routing stays untouched. Developers building on-device multimodal apps can grab the code and weights from GitHub and Hugging Face to run large models where cloud calls are impractical. It also shows open-source Chinese labs pulling ahead on mobile inference efficiency, a space Apple and Qualcomm stack owners care about.

OpenBMB@OpenBMBSource
Tomorrow 08:00, the daily lands in your inboxTelegram channel or email. Same screening as this page, no ads.
ModelsUS vs ChinaMulti-sourceSelected13:20
DeepInfer Release Draws Criticism Over Heterogeneous Hardware Support

The debate centres on whether DeepInfer's reported throughput depends on a tightly controlled, homogeneous GPU fleet rather than general infrastructure design. Engineers planning large-scale inference deployments on GB200 clusters can weigh whether NVIDIA Dynamo plus 3FS achieves comparable results outside DeepSeek's own setup.

Event
Teortaxes@teortaxesTexSource
ModelsBuildersSelected13:20
Meta Publishes Technical Report on 30B Muse Glimmer Model

The notable part is the local deployment angle: a 30B agentic model that fits a single consumer GPU at 4-bit reduces dependence on cloud APIs and per-token costs. Developers building tool-use agents on local machines can study the distillation and quantization recipe for their own setups. It competes directly with similarly-sized open-weight models, so benchmark claims are worth verifying against your own workload.

Official accountMeta AI@AIatMetaSource
ModelsBuildersSelected10:25
iFlytek Spark-X2.6-4B Launches With 1M-Token Context Under Apache 2.0

A 4B model handling a 1M-token context window pushes long-document workloads onto small hardware, making local long-context inference practical on consumer GPUs. The Apache 2.0 license allows unrestricted commercial use, a contrast to models with usage restrictions. Developers building retrieval-free long-context applications can deploy it directly through vLLM.

Event
Official accountvLLM@vllm_projectSource
ModelsBuildersSelected08:37
FastH3-Omni Ships Realtime Video Generation with Open Weights

Day-0 vLLM-Omni support plus consumer RTX GPU compatibility means individuals and small teams can experiment with realtime video generation without data-centre hardware. Open training code also lets practitioners fine-tune or extend the model for their own pipelines. Developers building video generation features in ASEAN startups can now prototype on affordable local hardware.

Official accountvLLM@vllm_projectSource
ModelsBuildersSelected02:53
Épi research agent sets 120 records on math problems

The fixed verifier design is the key detail: it keeps the agent's self-improvement honest by preventing it from altering how its own outputs are judged. Builders working on long-running agents can borrow the pattern of persistent history, versioned branches and independent review. The Épi-turbo comparison against Codex on FrontierOR offers a concrete cost-versus-accuracy reference point for teams automating solver generation.

DAIR.AI@dair_aiSource

Only the latest 2000 items are listed; for older ones see the daily archive