gpt-oss-20b vs Kimi-Linear-48B-A3B-Instruct

Specs, VRAM requirements and download trends — updated 7 September 2026.

openai · A
Params
21.5 B
Context
131,072
30d
6.6 M
apache-2.0 · commercial OK
moonshotai · B
Params
49.1 B
Context
30d
191 K
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification gpt-oss-20b Kimi-Linear-48B-A3B-Instruct
Parameters 21.5 B 49.1 B
Architecture GptOssForCausalLM KimiLinearForCausalLM
Context length 131,072
Licence apache-2.0 mit
Commercial use Allowed Allowed
Languages
Downloads 30d 6,646,564 190,802
Downloads all time 98.6 M 1.2 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-08-04 2025-10-30

Download trend

Daily snapshots, last 57 days (28 Jul – 22 Sep)

8.6 M176 K
gpt-oss-20b Kimi-Linear-48B-A3B-Instruct

VRAM side by side

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

gpt-oss-20b · fp16 @ 128K ctx 82.4 GB / 24 GB
❌ Won’t fit
Kimi-Linear-48B-A3B-Instruct · fp16 115.9 GB / 24 GB
❌ Won’t fit

Adjacent comparisons