gpt-oss-120b vs llama-3-70b-instruct-awq

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

openai · A
Params
120.4 B
Context
131,072
30d
4.2 M
apache-2.0 · commercial OK
casperhansen · B
Params
70.6 B
Context
8,192
30d
249 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification gpt-oss-120b llama-3-70b-instruct-awq
Parameters 120.4 B 70.6 B
Architecture GptOssForCausalLM LlamaForCausalLM
Context length 131,072 8,192
Licence apache-2.0
Commercial use Allowed Unknown
Languages
Downloads 30d 4,221,708 248,810
Downloads all time 48.6 M 1.4 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-08-04 2024-04-18

Download trend

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

4.3 M244 K
gpt-oss-120b llama-3-70b-instruct-awq

VRAM side by side

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

llama-3-70b-instruct-awq · fp16 54.8 GB / 24 GB
❌ Won’t fit
gpt-oss-120b · fp16 @ 128K ctx 433.0 GB / 24 GB
❌ Won’t fit

Adjacent comparisons