gpt-oss-120b vs Llama-3.3-70B-Instruct
Specs, VRAM requirements and download trends — updated 10 November 2026.
openai · A · Open weights
Params
120.4 B
Context
131,072
30d
2.4 M
apache-2.0 · commercial OK
meta-llama · B · Open weights
Params
70.6 B
Context
—
30d
351 K
llama3.3 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gpt-oss-120b | Llama-3.3-70B-Instruct |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 120.4 B | 70.6 B |
| Architecture | GptOssForCausalLM | LlamaForCausalLM |
| Context length | 131,072 | 128,000 |
| Licence | apache-2.0 | llama3.3 |
| Commercial use | Allowed | Conditional |
| Languages | — | 8 |
| Downloads 30d | 2,417,644 | 350,898 |
| Downloads all time | 62.0 M | 15.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2025-08-04 | 2024-11-26 |
| API input price / 1M tokens | $0.15 | $0.71 |
| API output price / 1M tokens | $0.60 | $0.71 |
| Est. cost per 1M input + 1M output tokens | $0.75 | $1.42 |
| Cached input / 1M tokens | $0.075 | $0.71 |
| AA Intelligence Index | 3.8 | — |
| AA Coding Index | 30.4 | 11.9 |
| AA Agentic Index | 3.7 | — |
| Max output tokens | 65,536 | 115,200 |
| API providers | 22 | 8 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
gpt-oss-120b
$0.75
Llama-3.3-70B-Instruct
$1.42
gpt-oss-120b is 1.9× cheaper at list price.
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
5.5 M210 K
gpt-oss-120b
Llama-3.3-70B-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Llama-3.3-70B-Instruct · fp16
166.3 GB / 24 GB
gpt-oss-120b · fp16 @ 128K ctx
433.0 GB / 24 GB