gpt-oss-20b vs Qwen3.8-27B-OBLITERATED

Specs, VRAM requirements and download trends — updated 21 September 2026.

openai · A
Params
21.5 B
Context
131,072
30d
6.7 M
apache-2.0 · commercial OK
OBLITERATUS · B
Params
27.8 B
Context
30d
1.2 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification gpt-oss-20b Qwen3.8-27B-OBLITERATED
Parameters 21.5 B 27.8 B
Architecture GptOssForCausalLM Qwen3_5ForConditionalGeneration
Context length 131,072
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages
Downloads 30d 6,658,531 1,235,942
Downloads all time 98.5 M 1.4 M
Quantizations on the Hub SAFETENSORS GGUF, SAFETENSORS
Gated No No
First seen on the Hub 2025-08-04 2026-08-19

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

8.6 M245 K
gpt-oss-20b Qwen3.8-27B-OBLITERATED

VRAM side by side

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

Qwen3.8-27B-OBLITERATED · Q4_K_M 23.2 GB / 24 GB
⚠️ Tight — reduce context
gpt-oss-20b · fp16 @ 128K ctx 82.4 GB / 24 GB
❌ Won’t fit
Qwen3.8-27B-OBLITERATED · fp16 126.9 GB / 24 GB
❌ Won’t fit

Adjacent comparisons