gemma-3-1b-it vs NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark

Specs, VRAM requirements and download trends — updated 21 September 2026.

google · A
Params
1.0 B
Context
30d
3.1 M
gemma licence · conditional
nvidia · B
Params
760 M
Context
1,048,576
30d
241 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification gemma-3-1b-it NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark
Parameters 1.0 B 760 M
Architecture Gemma3ForCausalLM Qwen3DSparkModel
Context length 1,048,576
Licence gemma other
Commercial use Conditional Unknown
Languages
Downloads 30d 3,077,946 241,067
Downloads all time 51.6 M 341 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated Yes — accept licence No
First seen on the Hub 2025-03-10 2026-08-05

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

5.2 M191 K
gemma-3-1b-it NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

gemma-3-1b-it · fp16 2.8 GB / 24 GB
✅ Runs comfortably
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark · fp16 @ 1024K ctx 16.6 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons