Official weight and serving conditions explained, not our model run
E4B weights, precision and runtime memory →
The E4B previewed in the October 15 source now has released artifacts.
NVIDIA · Released 2026-10-23
Nemotron 3.5 Bolt E4B
A text model post-trained from Gemma-4-E4B, with 8B total/4B effective parameters and BF16/Q4_K_M GGUF artifacts. 4GB names a target VRAM envelope; file size, cache and system memory differ. AA has no numeric result, Pi has no matching result, and Physics video does not apply.
Original model explanation ↗No comparable leaderboard score is included yet. Explore the evaluations and examples below.
Evaluations: conditions and results
NVIDIA model card and vendor tests
Fixed 4GB card and GGUF conditions ↗
Full precision and its separate serving recipe
BF16 artifact of the same E4B model ↗
How this capability connects to works and uses
Publisher application account, not our on-device experience
Text and vision layers in the Reachy Mini example ↗
NVIDIA model evolution
- Nemotron 3.5 Super VL · 正式发布
The 120B-total, 12B-active multimodal model launches with public weights, training materials and hosted routes; model cards specify precision and hardware.
Original release ↗ - Nemotron 3.5 Bolt 74B-A9B 24GB · 正式发布
The 74B-total, 9B-active local-agent model launches. 24GB names a specific quantization recipe; long-context GGUF requires more memory. The October 15 source still described E4B as a later plan; its October 23 release is listed separately.
Original release ↗ - Cosmos3-H-Dreams · 动作条件手术模拟
A specialist continues endoscopic video from two-arm actions; distinguish two-/four-step weights and the GPU runtime. Clinical validity and a matching score in the existing physics board remain unestablished.
Original release ↗ - Nemotron 3.5 Bolt E4B · BF16与4GB制品公开
The research and card date GA to October 23: Gemma-4-E4B post-training, 8B total/4B effective, with BF16 and Q4_K_M GGUF artifacts. 4GB describes a target VRAM envelope, not total system memory.
Original release ↗