gemma-3-1b-it vs Llama-3.2-1B-Instruct-FP8

Specs, VRAM requirements and download trends — updated 6 August 2026.

google · A
Params
1.0 B
Context
30d
4.7 M
gemma licence · conditional
RedHatAI · B
Params
1.5 B
Context
131,072
30d
799 K
llama3.2 licence · conditional

Specification comparison

Differences are highlighted; identical values are muted.

Specification gemma-3-1b-it Llama-3.2-1B-Instruct-FP8
Parameters 1.0 B 1.5 B
Architecture Gemma3ForCausalLM LlamaForCausalLM
Context length 131,072
Licence gemma llama3.2
Commercial use Conditional Conditional
Languages 8
Downloads 30d 4,749,309 798,879
Downloads all time 46.4 M 6.5 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated Yes — accept licence No
First seen on the Hub 2025-03-10 2024-09-26

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

4.7 M760 K
gemma-3-1b-it Llama-3.2-1B-Instruct-FP8

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
Llama-3.2-1B-Instruct-FP8 · fp16 @ 128K ctx 6.3 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons