gpt-oss-20b vs Qwen3-14B-AWQ

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

openai · A
Params
21.5 B
Context
131,072
30d
8.6 M
apache-2.0 · commercial OK
Qwen · B
Params
14.8 B
Context
40,960
30d
2.4 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification gpt-oss-20b Qwen3-14B-AWQ
Parameters 21.5 B 14.8 B
Architecture GptOssForCausalLM Qwen3ForCausalLM
Context length 131,072 40,960
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages
Downloads 30d 8,616,555 2,388,031
Downloads all time 87.8 M 10.9 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-08-04 2025-05-01

Download trend

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

8.6 M2.4 M
gpt-oss-20b Qwen3-14B-AWQ

VRAM side by side

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

Qwen3-14B-AWQ · fp16 13.7 GB / 24 GB
✅ Runs comfortably
gpt-oss-20b · fp16 @ 128K ctx 82.4 GB / 24 GB
❌ Won’t fit

Adjacent comparisons