Qwen2.5-3B-Instruct vs Qwen2.5-7B-Instruct-GPTQ-Int4
Specs, VRAM requirements and download trends — updated 31 August 2026.
Qwen · B
Params
7.6 B
Context
32,768
30d
186 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-3B-Instruct | Qwen2.5-7B-Instruct-GPTQ-Int4 |
|---|---|---|
| Parameters | 3.1 B | 7.6 B |
| Architecture | Qwen2ForCausalLM | Qwen2ForCausalLM |
| Context length | 32,768 | 32,768 |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 4,751,814 | 186,254 |
| Downloads all time | 120.0 M | 1.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-17 | 2024-09-17 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
7.6 M186 K
Qwen2.5-3B-Instruct
Qwen2.5-7B-Instruct-GPTQ-Int4
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-3B-Instruct · fp16
7.8 GB / 24 GB
Qwen2.5-7B-Instruct-GPTQ-Int4 · fp16
7.8 GB / 24 GB