NVIDIA's Nemotron-3.5-Bolt-74B (9B active, 24GB) trends on Hugging Face
nvidia · hf · 2026-10-17
NVIDIA's Nemotron-3.5-Bolt-74B-A9B-24GB is trending on Hugging Face. The image-text-to-text conversational model has 74B total parameters with roughly 9B active, ships in transformers/safetensors format using the nemotronhomni architecture, and its 24GB footprint makes it attractive for local deployment.
Related event: NVIDIA ships Nemotron 3.5 Bolt, a 74B MoE model that fits in 24GB VRAM(5 posts)→
More from Models
- More on Claude's ECDSA seed revelation: the Wikipedia context — scaling01 · 2026-10-17
- Claude cracks 30-year mystery: ECDSA curve seeds were just RNG output — scaling01 · 2026-10-17
- Perplexity decider v1.2 lands #3 on Decision Index as longer training erodes backbone skills — antoine_chaffin · 2026-10-17
- Perplexity's 4B decider model distills from its 27B sibling using the same training recipe — antoine_chaffin · 2026-10-17
- Perplexity traces decider v1.2 regressions to longer training, mitigates via model souping — antoine_chaffin · 2026-10-17
- Perplexity details decider data hygiene: official splits only, deduped, 16.6% of one stage — antoine_chaffin · 2026-10-17