gpt-oss-20b vs Qwen2.5-32B-Instruct-GPTQ-Int4

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
32.8 B
Context
32,768
30d
492 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification gpt-oss-20b Qwen2.5-32B-Instruct-GPTQ-Int4
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 8,616,555 491,706
Downloads all time 87.8 M 4.2 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-08-04 2024-09-17

Download trend

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

8.6 M464 K
gpt-oss-20b Qwen2.5-32B-Instruct-GPTQ-Int4

VRAM side by side

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

Qwen2.5-32B-Instruct-GPTQ-Int4 · fp16 26.7 GB / 24 GB
❌ Won’t fit
gpt-oss-20b · fp16 @ 128K ctx 82.4 GB / 24 GB
❌ Won’t fit

Adjacent comparisons