Qwen3-4B vs Qwen2.5-Coder-7B-Instruct-4bit
Specs, VRAM requirements and download trends — updated 10 November 2026.
mlx-community · B · Open weights
Params
1.2 B
Context
32,768
30d
264 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-4B | Qwen2.5-Coder-7B-Instruct-4bit |
|---|---|---|
| Parameters | 4.0 B | 1.2 B |
| Architecture | Qwen3ForCausalLM | Qwen2ForCausalLM |
| Context length | 40,960 | 32,768 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 4,013,632 | 263,968 |
| Downloads all time | 94.5 M | 1.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-27 | 2024-09-18 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
12.6 M177 K
Qwen3-4B
Qwen2.5-Coder-7B-Instruct-4bit
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-Coder-7B-Instruct-4bit · fp16
5.4 GB / 24 GB
Qwen3-4B · fp16
10.0 GB / 24 GB