Qwen2.5-7B-Instruct vs starcoder2-3b

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

Qwen · A

Qwen2.5-7B-Instruct

Params

7.6 B

Context

32,768

30d

12.1 M

apache-2.0 · commercial OK

bigcode · B

Params

3.0 B

Context

16,384

30d

184 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen2.5-7B-Instruct	starcoder2-3b
Parameters	7.6 B	3.0 B
Architecture	Qwen2ForCausalLM	Starcoder2ForCausalLM
Context length	32,768	16,384
Licence	apache-2.0	bigcode-openrail-m
Commercial use	Allowed	Unknown
Languages	1	—
Downloads 30d	12,117,940	183,925
Downloads all time	165.8 M	7.4 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2024-09-16	2023-11-29

Download trend

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

12.2 M183 K

Qwen2.5-7B-Instruct starcoder2-3b

VRAM side by side

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

starcoder2-3b · fp16 14.3 GB / 24 GB

✅ Runs comfortably

Qwen2.5-7B-Instruct · fp16 18.4 GB / 24 GB

✅ Runs comfortably

Adjacent comparisons

Qwen3-8B vs Qwen2.5-7B-Instruct

Qwen2.5-7B-Instruct vs Llama-3.1-8B-Instruct

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

Qwen2.5-7B-Instruct vs Qwen3.6-35B-A3B-NVFP4

Qwen2.5-7B-Instruct vs granite-4.1-8b

Qwen2.5-7B-Instruct vs gpt-oss-20b