NVIDIA ships Nemotron 3.5 Bolt E4B, an 8B/4B-effective model beating Gemma-4 and Qwen3.5
mervenoyann · x · 2026-10-24
NVIDIA released an E4B version of Nemotron 3.5 Bolt (8B params, 4B effective) that it says outperforms Gemma-4 and Qwen3.5 at much lower latency, scoring 70.2 on its representative benchmark. It ships with a DFlash drafter for faster decoding, and quants from ggml and unsloth are already available.
More from Models
- Suspicious new GitHub accounts reference Qwen4 in Alibaba T-Head repo PRs — brainExploded99 · 2026-10-24
- Kimi K3.1 Pro takes on the pelican-on-a-bicycle 3D test: beats Opus 5, trails 5.5 — blaind0 · 2026-10-24
- Kimi's $19 coding plan roasted: 5-hour limit hit before a single meaningful line of code — teortaxesTex · 2026-10-24
- Kimi's new model reportedly 30x costlier to serve than V4.1 Flash, sparking skepticism — teortaxesTex · 2026-10-24
- Unverified Claim: Kimi K3.1 Suspected of Being Distilled from Opus, Sparks Debate — imjustnewatai · 2026-10-24
- Community claims Kimi k3.1 is the most 'benchmaxxed' model ever, alleging distillation — imjustnewatai · 2026-10-24