gpt-oss-120b vs Hermes-3-Llama-3.1-405B
Specs, VRAM requirements and download trends — updated 25 October 2026.
openai · A · Open weights
Params
120.4 B
Context
131,072
30d
2.9 M
apache-2.0 · commercial OK
NousResearch · B · Open weights
Params
405.9 B
Context
131,072
30d
1 K
llama3 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gpt-oss-120b | Hermes-3-Llama-3.1-405B |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 120.4 B | 405.9 B |
| Architecture | GptOssForCausalLM | LlamaForCausalLM |
| Context length | 131,072 | 131,072 |
| Licence | apache-2.0 | llama3 |
| Commercial use | Allowed | Conditional |
| Languages | — | 1 |
| Downloads 30d | 2,893,802 | 1,327 |
| Downloads all time | 60.5 M | 958 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-08-04 | 2024-08-13 |
| API input price / 1M tokens | $0.15 | $1.00 |
| API output price / 1M tokens | $0.60 | $1.00 |
| Est. cost per 1M input + 1M output tokens | $0.75 | $2.00 |
| Cached input / 1M tokens | $0.075 | — |
| AA Intelligence Index | 11.6 | — |
| AA Coding Index | 30.4 | — |
| AA Agentic Index | 3.7 | — |
| Max output tokens | 65,536 | 16,384 |
| API providers | 22 | 1 |
| Tool calling | Yes | No |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
gpt-oss-120b
$0.75
Hermes-3-Llama-3.1-405B
$2.00
gpt-oss-120b is 2.7× cheaper at list price.
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
5.5 M1 K
gpt-oss-120b
Hermes-3-Llama-3.1-405B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gpt-oss-120b · fp16 @ 128K ctx
433.0 GB / 24 GB
Hermes-3-Llama-3.1-405B · fp16 @ 128K ctx
1,867.4 GB / 24 GB