gpt-oss-20b vs Qwen2.5-Coder-32B-Instruct-AWQ
Specs, VRAM requirements and download trends — updated 20 September 2026.
Qwen · B
Params
32.8 B
Context
32,768
30d
1.5 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gpt-oss-20b | Qwen2.5-Coder-32B-Instruct-AWQ |
|---|---|---|
| Parameters | 21.5 B | 32.8 B |
| Architecture | GptOssForCausalLM | Qwen2ForCausalLM |
| Context length | 131,072 | 32,768 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 6,708,152 | 1,500,032 |
| Downloads all time | 98.3 M | 11.3 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-08-04 | 2024-11-09 |
Download trend
Daily snapshots, last 55 days (28 Jul – 20 Sep)
8.6 M1.3 M
gpt-oss-20b
Qwen2.5-Coder-32B-Instruct-AWQ
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-Coder-32B-Instruct-AWQ · fp16
26.7 GB / 24 GB
gpt-oss-20b · fp16 @ 128K ctx
82.4 GB / 24 GB