Unsloth Releases Inkling-Small Multimodal MoE Model
unsloth · hf · 2026-07-30
Unsloth has released Inkling-Small on Hugging Face. The model is fine-tuned from thinkingmachines/Inkling-Small and utilizes a Mixture-of-Experts (MoE) architecture.
It supports multimodal conversational capabilities, including image-text-to-text and audio-text-to-text. The weights are available in transformers and safetensors formats under the Apache-2.0 license.
Related event: Inkling-Small: 276B params, 12B active, open-source tops ARC(48 posts)→
More from Models
- Why are sub-15B open models so rare now? Labs seem to have settled on 24-27B minimum — Hot_Example_4456 · 2026-10-16
- User spots model openly generating "ideal responses" to train other models — liminal_bardo · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Gemma 4 31B QAT on one 24GB card: 46 tok/s plain, ~80 with draft model on RTX 4090 — Subject_Poet_3861 · 2026-10-16
- JevBench v1.7.46 leaderboard: new d1-ultra tops 32 API systems at 76.1 composite — airesearch12 · 2026-10-16
- Team of 5 mulls dropping ChatGPT Pro for Business as OpenAI quota parity stays unclear — bettercallfool · 2026-10-16