Title: gpt-oss-20b vs gpt-oss-120b: Parametri, Licence %E2%80%94 LLM EU
Canonical: https://llmeu.com/lv/compare/gpt-oss-20b-vs-gpt-oss-120b/
Markdown mirror: https://llmeu.com/lv/compare/gpt-oss-20b-vs-gpt-oss-120b.md
Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json

# gpt-oss-20b vs gpt-oss-120b

Sal%C4%ABdziniet divus l%C4%ABdz %C4%8Detrus mode%C4%BCus blakus p%C4%93c laukiem, kas nosaka izvieto%C5%A1anu: konteksts, cena, re%C4%A3ions, licence, valodas, mitin%C4%81%C5%A1ana un tas, kas ir verific%C4%93ts.

Ja divi mode%C4%BCi at%C5%A1%C4%B7iras, %C5%A1%C4%AB tabula par%C4%81da at%C5%A1%C4%B7ir%C4%ABbu un apst%C4%81jas. LLM EU nepublic%C4%93 uzvar%C4%93t%C4%81ja z%C4%ABmi bez dokument%C4%93ta rezult%C4%81ta %C5%A1im uzdevumam, un tr%C5%ABksto%C5%A1s skaitlis paliek tr%C5%ABksto%C5%A1s, nevis k%C4%BC%C5%ABst par nulli.

## Kad to izmantot

### [gpt-oss-20b](/lv/models/gpt-oss-20b/)

#### Stipr%C4%81s puses

- runs in about 16GB of memory
- same 131,072-token window as the larger sibling
- Apache-2.0 licence
- reasoning-effort control

#### Ierobe%C5%BEojumi

- quality clearly below the 120B model
- harmony response format required
- no evaluation has been run by LLM EU

#### Uzdevumi

[Sprie%C5%A1ana](/lv/tasks/reasoning/), [Zemas izmaksas](/lv/tasks/cheap/), [Kod%C4%93%C5%A1ana](/lv/tasks/coding/), [Ieg%C5%AB%C5%A1ana (RAG)](/lv/tasks/rag/)

### [gpt-oss-120b](/lv/models/gpt-oss-120b/)

#### Stipr%C4%81s puses

- Apache-2.0 licence with no user threshold
- runs on a single 80GB accelerator
- configurable reasoning effort with full chain-of-thought access
- native function calling, browsing and structured output

#### Ierobe%C5%BEojumi

- requires the harmony response format; other prompt templates degrade it
- 117B parameters must be resident even though only 5.1B are active
- chain-of-thought output is not intended for end users

#### Uzdevumi

[Sprie%C5%A1ana](/lv/tasks/reasoning/), [Kod%C4%93%C5%A1ana](/lv/tasks/coding/), [Ieg%C5%AB%C5%A1ana (RAG)](/lv/tasks/rag/), [Kopsavilk%C5%A1ana](/lv/tasks/summarization/)

**Uzdevumi:** [Sprie%C5%A1ana](/lv/tasks/reasoning/), [Kod%C4%93%C5%A1ana](/lv/tasks/coding/), [Ieg%C5%AB%C5%A1ana (RAG)](/lv/tasks/rag/)

## Sal%C4%ABdzin%C4%81t mode%C4%BCus

- [Command A+ (05-2026) vs gpt-oss-120b](/lv/compare/command-a-plus-05-2026-vs-gpt-oss-120b/)
- [Command R (08-2024) vs gpt-oss-20b](/lv/compare/command-r-08-2024-vs-gpt-oss-20b/)
- [DeepSeek Coder V2 Lite Instruct vs gpt-oss-20b](/lv/compare/deepseek-coder-v2-lite-instruct-vs-gpt-oss-20b/)
- [DeepSeek R1 Distill Qwen 14B vs gpt-oss-20b](/lv/compare/deepseek-r1-distill-qwen-14b-vs-gpt-oss-20b/)
- [DeepSeek-R1-Distill-Qwen-32B vs gpt-oss-20b](/lv/compare/deepseek-r1-distill-qwen-32b-vs-gpt-oss-20b/)
- [DeepSeek V2 Lite vs gpt-oss-20b](/lv/compare/deepseek-v2-lite-vs-gpt-oss-20b/)