Kimi K3's weights were released on Hugging Face on 26 July, ten days after the model's hosted launch, enabling autonomous agents to run on local hardware and removing the friction of data leaving the …
Bloomberg News reported that Chinese AI startup Moonshot AI has access to approximately 20,000 Nvidia Hopper-generation chips through a computing agreement with Alibaba Group, providing key compute fo…
AirLLM, an Apache-2.0 Python library, enables running large language models like Llama 3.1 405B on 8GB of VRAM and DeepSeek-V3 671B on ~12GB without quantization, by streaming one layer or MoE expert …
On July 27, China's Moonshot AI released its most powerful AI model, Kimi K3, as free open-source software, allowing any government, company, or individual to run and retrain it without paying licensi…
DeepSeek's V4-Flash API pricing undercuts OpenAI and Anthropic, listed at $0.14 per million cache-miss input tokens and $0.28 per million output tokens, compared to OpenAI's GPT-5.6 Luna at $0.20 inpu…
AirLLM, an open-source inference library, now supports running the 2.8T-parameter Kimi K3 model on a single 4GB GPU, using only 3.72GB of VRAM on an RTX 6000 Ada, by streaming one expert at a time for…
Anthropic's Claude Opus 5 generates complete 3D games from single prompts, including a first-person shooter, a kart racer, and a Minecraft clone, all without external assets, producing geometry, textu…
Benchmarking by an unnamed engineer shows AMD's MI355X GPU delivers lower cost per million tokens than Nvidia's B300 for serving Kimi K3, due to memory bandwidth and quantization fitting the model on …
Wafer, an AI infrastructure provider founded by Emilio Andere and Steven Arellano, reported that running Kimi K3 on eight AMD MI355X GPUs delivered 48 tokens per second per dollar, outperforming Nvidi…
AI News Digest for August 2 covers 29 stories, including Kimi K3 on MI355X offering better performance per dollar than B300, Figure AI's F.03 ladder climb raising autonomy or OSHA concerns, and Google…
AMD's MI355X GPU achieved 48 tokens/sec per dollar running the 2.8T-parameter Kimi K3 model, outperforming Nvidia's B300 (33 tokens/sec) and B200 (7 tokens/sec), according to benchmarks from Wafer. Th…
AMD's Instinct MI355X GPUs now run Moonshot AI's 2.8-trillion-parameter Kimi K3 model at 952 tokens per second per node, undercutting Nvidia's B300 on cost per token despite Nvidia's 1.65x raw through…
DeepSeek V4 Flash scored 82.7 on Terminal-Bench 2.1, outperforming Anthropic's Claude Fable 5 at 80.5 while being priced at $0.14 per million input tokens and $0.28 per million output tokens, roughly …
Wafer's benchmark shows AMD's MI355X GPUs deliver 952 tok/s/node on Kimi K3, outperforming NVIDIA's B300 on performance per dollar at 48 tok/s/$ versus 33 tok/s/$, despite B300's higher aggregate thro…
Three AI model releases in late July 2025 — Moonshot AI's Kimi K3, Anthropic's Claude Opus 5, and Microsoft's MAI models — signal that the competitive axis has shifted from capability to cost, with fr…
On July 28, 2026, Moonshot AI, Anthropic, and Microsoft each released major AI models, signaling a market shift toward cost-efficient and open-weight models. Moonshot AI open-sourced Kimi K3, a 2.8-tr…
Dropstone 1.7 updates all three model tiers, with Heavy moving to Kimi K3, which scores 57.1 on the Artificial Analysis Intelligence Index, the highest of any open-weight model and the first to surpas…
On July 16, Beijing-based Moonshot AI released Kimi K3, a 2.8-trillion-parameter open-weight AI model, which independent accounts call the largest ever built. Three days later, Moonshot paused new sig…
Code Arena, an AI evaluation platform at arena.ai, launched an Image-to-WebDev benchmark on April 15, 2026, ranking large language models on converting UI screenshots into functional web code, with An…
Moonshot AI's open-weight Kimi K3 model matches Anthropic's Claude Sonnet 5 API pricing token-for-token while promising performance comparable to Claude Opus 4.8, ending the era where open-weight mode…