Qwen2.5-3B-Instruct vs gemma-1.1-2b-it

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

Qwen · A

Qwen2.5-3B-Instruct

Params

3.1 B

Context

32,768

30d

6.0 M

google · B

gemma-1.1-2b-it

Params

2.5 B

Context

—

30d

209 K

gemma licence · conditional

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen2.5-3B-Instruct	gemma-1.1-2b-it
Parameters	3.1 B	2.5 B
Architecture	Qwen2ForCausalLM	GemmaForCausalLM
Context length	32,768	—
Licence	other	gemma
Commercial use	Unknown	Conditional
Languages	1	—
Downloads 30d	5,952,246	209,209
Downloads all time	110.0 M	3.2 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	Yes — accept licence
First seen on the Hub	2024-09-17	2024-03-26

Download trend

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

6.0 M200 K

Qwen2.5-3B-Instruct gemma-1.1-2b-it

VRAM side by side

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

gemma-1.1-2b-it · fp16 6.4 GB / 24 GB

✅ Runs comfortably

Qwen2.5-3B-Instruct · fp16 7.8 GB / 24 GB

✅ Runs comfortably

Adjacent comparisons

Qwen2.5-1.5B-Instruct vs Qwen2.5-3B-Instruct

Qwen3-8B vs Qwen2.5-3B-Instruct

Qwen3-1.7B vs Qwen2.5-3B-Instruct

Qwen2.5-7B-Instruct vs Qwen2.5-3B-Instruct

Llama-3.2-1B-Instruct vs Qwen2.5-3B-Instruct

Qwen2.5-3B-Instruct vs Qwen3-4B