Kimi Launches Open-Source Reasoning VLM
mervenoyann · x · 2026-07-17
The quoted content introduces Kimi-VL-A3B-Thinking: an open-source, MIT-licensed reasoning VLM, claimed to be the first "capable" open-source reasoning vision-language model.
Key highlights:
- Features only 2.8B activated params
- Possesses agentic capabilities
- The authors claim its performance exceeds that of gpt-4o
The original post simply expresses long-standing confidence in Kimi, with the core details concentrated in the cited model introduction and test results.
Related event: Kimi Releases Open-Source Reasoning Vision-Language Model(2 posts)→
More from Multimodal
- 3D ResNet Paper Crosses 3,000 Citations Eight Years After CVPR 2018 — HirokatuKataoka · 2026-09-11
- Non-coder builds full-featured Android ComfyUI client with ChatGPT, submits to Google Play — ComfierUI · 2026-09-11
- FastH3-Live hits 22fps: acceleration node benchmarks and the --vram-headroom trick — spartong945 · 2026-09-11
- Midjourney style code share: --sref 2912175708 — tisch_eins · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- MiniMax H3 MAX nails cooking anime clips: 15-second curry demo with prompts shared — Hailuo_AI · 2026-09-11