Basalt

the ai lab for open foundation models.

[Basalt @basaltlabs]

the experiment has concluded 🫪

[FaceDev @facedevstuff]

video out now, enjoy!

[Basalt @basaltlabs]

Everything is released under MIT: weights, tokenizer, eval harness, and training checkpoints.

No waitlist, no API keys, no usage tiers. Download the weights and run Monolith-1.0 on your own hardware, or try it now at https://t.co/8ozmeD7xqz.

If you hit something that should be hard, bring it.

[Basalt @basaltlabs]

Introducing Monolith-1.0: Frontier Reasoning, Open Weights

- 1.57T-param Mixture-of-Experts, 49.5B active per token
- Native 1M-token context (2²⁰), extended via a two-stage YaRN curriculum
- Trained on 60T tokens across 12,288 Ascend 910C NPUs
- Frontier SOTA open-source model as of July 2026: 95.9% GPQA Diamond, 96.2% MMLU-Pro, 90%+ AIME 2025
- MIT-licensed weights, tokenizer, and eval harness

No waitlist - open the chat and give it something that should be hard.

Chat: https://t.co/8x13RXoPY4

[Basalt @basaltlabs]

Monolith-1.0 was trained on 60 trillion tokens across 12,288 Huawei Ascend 910C NPUs.

The stack uses 3D parallelism, sequence parallelism, and ZeRO-style optimizer sharding tuned for the Ascend interconnect, with deterministic checkpointing throughout the run.

The model trained end-to-end without loss spikes or rollback restarts.

[Kimi.ai @Kimi_Moonshot]

Introducing Kimi K3: Open Frontier Intelligence

🔹 2.8 Trillion Parameters, 1 Million Context, Native Multimodal
🔹 Kimi Delta Attention enables up to 6.3x faster decoding in million-token contexts
🔹 Attention Residuals deliver ~25% higher training efficiency at <2% additional cost
🔹 Built for long-horizon agentic coding and self-evolving workflows

Kimi K3 is now live on on https://t.co/zrk6zZxZUo, Kimi Work, Kimi Code, and the Kimi API.
Open Weights by July 27, 2026.

🔗 API: https://t.co/XCrgjXAqMw
🔗 Tech blog: https://t.co/YTfiMSNM1f

[Z.ai @Zai_org]

Introducing GLM-5.2: Frontier Intelligence, Open Weights

- Significant improvements in coding and agentic tasks
- Strong long-horizon capabilities with a 1M context window
- Two levels of reasoning effort: GLM-5.2 (max) pushes the limits, while GLM-5.2 (high) strikes a strong balance between performance and token efficiency
- MIT-licensed open weights
- Same API pricing as GLM-5.1

Tech Blog: https://t.co/LAsxUdN0JZ
Weights: https://t.co/g0A1C4UWx4
API: https://t.co/Kc3E22cbN7
Coding Plan: https://t.co/Nk8Y98HNhU
Chat: https://t.co/WCqWT0qCQb

[Kimi.ai @Kimi_Moonshot]

🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced!

🔷 Improved coding & agent performance over K2.6: +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite.
🔷 Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6.
🔷 Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates.

⚡️ 6x High-Speed Mode coming soon!
🔌 Available today via Kimi API and Kimi Code.

🔗 Kimi Code: https://t.co/uvoSJKyGCY
🔗 API: https://t.co/EOZkbOwCN4