Skip to content
Weights Not Walls
Menu

openai

gpt-oss-120b

Reviewed
Size
117B parametersfrom the GGUF metadata of a conversion, because this repo's own weights are packed: ggml-org/gpt-oss-120b-GGUF
Licence
unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
On the Hub since
4 Aug 2025the date the repo was created
Context length
128k tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)GptOssForCausalLM
On Hugging Face
openai/gpt-oss-120b2.4M downloads in the last 30 days, 5.5k likes

Scores

24 independent results on 15 eval sets
GPQA diamondRe-run by Epoch AI
  • effort high75.8%±2.711 Dec 2025, log

Epoch's name: openai/gpt-oss-120b. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results

Mystery Game PuzzlesRe-run by Epoch AI
  • effort medium2.0%±1.427 Aug 2026, log
  • effort high0.0%27 Aug 2026, log

Epoch's name: gpt-oss-120b. Best closed model on this set: gpt-6.2-astra_max, 95.0% (OpenAI). All 148 results

OTIS Mock AIME 2024-2025Re-run by Epoch AI
  • effort high88.9%±4.511 Dec 2025, log

Epoch's name: openai/gpt-oss-120b. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 results

Epoch's name: gpt-oss-120b, openai/gpt-oss-120b. Best closed model on this set: gpt-5-2025-08-07_high, 88.0% (OpenAI). All 72 results

APEX-AgentsReported

Epoch's name: gpt-oss-120b. Best closed model on this set: gemini-4-carbon_unknown, 84.2% (Google DeepMind). All 66 results

CritPtReported

Epoch's name: openai/gpt-oss-120b. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results

DTBenchReported

Epoch's name: gpt-oss-120b. Best closed model on this set: claude-fable-5-2_unknown, 99.2% (Anthropic). All 241 results

Epoch's name: chutes/gpt-oss-120b. Best closed model on this set: gpt-5-2025-08-07_medium, 97.2% (OpenAI). All 61 results

Epoch's name: gpt-oss-120b. Best closed model on this set: gpt-5-2025-08-07_medium, 86.0% (OpenAI). All 49 results

LMCAReported

Epoch's name: gpt-oss-120b. Best closed model on this set: claude-fable-5-2_xhigh, 70.6% (Anthropic). All 203 results

Epoch's name: gpt-oss-120b. Best closed model on this set: claude-mythos-preview-early, 85.2% (Anthropic). All 49 results

SimpleBenchReported

Epoch's name: gpt-oss-120b. Best closed model on this set: claude-fable-5-2_unknown, 94.9% (Anthropic). All 125 results

Epoch's name: gpt-oss-120b. Best closed model on this set: claude-fable-5_high, 95.0% (Anthropic). All 29 results

Epoch's name: gpt-oss-120b. Best closed model on this set: gpt-5.5_unknown, 84.7% (OpenAI). All 202 results

WeirdMLReported

Epoch's name: gpt-oss-120b, openai/gpt-oss-120b. Best closed model on this set: gpt-6-astra_promax, 93.6% (OpenAI). All 173 results

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.29 GB, worked out from the model's config (openai/gpt-oss-120b), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

ggml-org/gpt-oss-120b-GGUF (converted by ggml-org), 391k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
MXFP459.0 GBfile size59.8 GB59.0 + 0.29 + 0.50
Commands
llama.cpp
llama-server -hf ggml-org/gpt-oss-120b-GGUF:MXFP4
Ollama
ollama run hf.co/ggml-org/gpt-oss-120b-GGUF:MXFP4
Download
hf download ggml-org/gpt-oss-120b-GGUF --include "gpt-oss-120b-MXFP4.gguf" --local-dir gpt-oss-120b-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX mxfp4mlx-community/gpt-oss-120b-MXFP4-Q859.0 GBfile size59.8 GB59.0 + 0.29 + 0.50Download page
MLX 8bitlmstudio-community/gpt-oss-120b-MLX-8bit115.6 GBfile size116.4 GB115.6 + 0.29 + 0.50Download page

Original weights

The maker's own weights are packed into integer tensors, so the safetensors header gives no size we can trust; the repo lists the real file sizes.

hf download openai/gpt-oss-120b --local-dir gpt-oss-120b
Other conversions (9; sizes not read)

The Hub tags 100 or more quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

22 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.

ProviderInOutContextPrecisionTokens/sFirst tokenUptime 24hToolsJSON
Near AI$0.03$0.15128kfp4840.5 s99.9%yesyes
Venice$0.03$0.15125kint4531.0 s100.0%yesno
deepinfra$0.037$0.17128knot given260.3 s?yesyes
CoreWeave$0.03$0.17128kfp41390.4 s98.9%yesyes
AkashML$0.03$0.19128kfp41270.5 s100.0%yesyes
Crusoe$0.05$0.25128kbf162120.3 s100.0%yesyes
novita$0.05$0.25128knot given1770.6 s?yesyes
Google$0.09$0.36128knot given2300.3 s99.7%noyes
Mancer 2$0.095$0.38128kfp81160.6 s99.0%yesyes
Sail Research$0.06$0.40128kfp41300.8 s100.0%yesyes
DigitalOcean$0.06$0.42125knot given580.9 s100.0%nono
ovhcloud$0.09$0.47128knot given340.4 s?yesyes
BaseTen$0.10$0.50125kfp41780.2 s99.7%yesyes
Amazon Bedrock$0.15$0.60128knot given1630.4 s99.8%yesno
Groq$0.15$0.60128knot given3430.2 s99.5%yesyes
Nebius$0.15$0.60128kfp41940.3 s100.0%yesyes
SiliconFlow$0.15$0.60128kfp8631.1 s100.0%noyes
Together$0.15$0.60128knot given740.3 s99.9%yesyes
Cerebras$0.35$0.75128kfp167190.2 s100.0%yesyes
Parasail$0.10$0.75128kfp41860.5 s100.0%yesyes
SambaNova$0.14$0.95128knot given3260.4 s99.3%yesno
featherless-ai???not given???not givennot given

Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.

curl https://router.huggingface.co/v1/chat/completions \ -H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \ -d '{"model": "openai/gpt-oss-120b:near-ai", "messages": [{"role": "user", "content": "Hello"}]}'

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Fine-tunes of this model

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.