Model intelligence.
Follow the changes. Understand what comes next.
NVIDIA NIM for LLM/VLM 2.1.6 Released: Five Models Enter Mainline Containers, Backend Upgraded to vLLM 0.32.0 & SGLang 0.5.22
NVIDIA has released NIM for LLM/VLM 2.1.6 (November 14, 2026). The update upgrades inference backends to vLLM 0.32.0 and SGLang 0.5.22, promotes deepseek-v4.1-flash, inkling-small, muse-glimmer, nemotron-3.5-super-vl-120b-a12b, and qwen3.8-27b to their first main releases, adds cached runtime manifests and optional startup warmup requests, and patches 99 unique security issues.
Latest stories03
Newest publishedExplore this company’s models & APIs ↗Explore provider coverage ↗
NVIDIA NIM for LLM/VLM 2.1.6 Released: Five Models Enter Mainline Containers, Backend Upgraded to vLLM 0.32.0 & SGLang 0.5.22
NVIDIA has released NIM for LLM/VLM 2.1.6 (November 14, 2026). The update upgrades inference backends to vLLM 0.32.0 and SGLang 0.5.22, promotes deepseek-v4.1-flash, inkling-small, muse-glimmer, nemotron-3.5-super-vl-120b-a12b, and qwen3.8-27b to their first main releases, adds cached runtime manifests and optional startup warmup requests, and patches 99 unique security issues.
NVIDIA Opens Nemotron 3.5 Transcribe Weights
NVIDIA released open weights for Nemotron 3.5 Transcribe on October 28, 2026 (Hugging Face ID nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B). It is an offline speech/audio model for about 40 languages, with speaker-attributed transcription, translation, and audio Q&A; up to about one hour of audio and a 65,536-token context; license OpenMDW-1.1. NVIDIA AI cites a 5.33% Open ASR English figure; the HF card’s nine-set mean is 4.71%. Different sources and timing. Artificial Analysis cites 2.8% AA-WER (third-party, unretested here). For reference only.
Nemotron 3.5 Super VL and Bolt: Specs, License, Runs on 24GB
NVIDIA released Nemotron 3.5 Super VL (120B MoE, 12B active, 1M context, vision) and Bolt 74B (from Super VL, 9B active, native 2-bit, ~24GB, still images/video) on October 15 under OpenMDW-1.1. On October 23 it added Bolt E4B—post-trained from Gemma 4 E4B, 8B total / 4B effective, text in and text out, 64K context. The “4GB” in the name is NVIDIA’s target memory envelope for its workloads; that is not the Q4_K_M weight file size (~6.18GB), and E4B is not a shrink of the 74B Bolt.