openai/gpt-oss-120b · Discussions

Can gpt-oss support local deployment on V100 GPU?

#134 opened 4 days ago by

SPGZXB

gpt-oss-120b has high possibility to generate response as part of reasoning

#133 opened 4 days ago by

tonyaw

AIME eval script does not score correctly some answers

👀 1

#132 opened 5 days ago by

ggerganov

Is it possible to use fine tuning on this model?

1

#131 opened 7 days ago by

Jameslxz11

assistantfinal, analysis keyword is contained in the huggingface gpt-oss-120 output. Is this intended?

#130 opened 7 days ago by

ml345

123

#129 opened 9 days ago by

petermu

Rename README.md to làm đẹp đoạn code của tôi được không ? tôi sẽ dán vào đây

#128 opened 11 days ago by

tranvanbest

How to deploy gpt oss 120B in Openshift AI platform

👍 1

1

#126 opened 12 days ago by

eselvam

how to run gpt-oss-120b by ollama using multi-gpu

1

#125 opened 13 days ago by

ssfyasuo

Is this demo powered by hugging face?

🤗 👍 1

2

#124 opened 13 days ago by

terobox

Very bad censorship

#123 opened 13 days ago by

YesIamKurt

how to exclude file in "original" folder while model download

6

#122 opened 14 days ago by

meetzuber

gpt-oss-120b works with OpenRouter + MCP servers, but not with locally hosted setup via LibreChat

#121 opened 14 days ago by

Byrdi

Create ابو الرشد ٢٠٢٥

#120 opened 16 days ago by

Shrif7roshdi

Update README.md

#119 opened 19 days ago by

Lorriea73

new version miss file,can't startup the model gpt-oss

1

#118 opened 19 days ago by

aidenpan0x

Fine tune 120b at 8 H100s getting cuda OOM error

4

#117 opened 19 days ago by

jinxu88

68.4 on Aider Polyglot with reasoning_effort: high

🔥 2

#116 opened 20 days ago by

Fernanda24

fix missing the `{% generation %}` keyword while using tokenizer.apply_chat_template(...return_assistant_tokens_mask=True)

#112 opened 21 days ago by

lllIIIlIlIk

Two clarifications on gpt-oss-120B hardware (fine-tuning vs inference, MoE VRAM)

#110 opened 21 days ago by

GazJ16

gpt-oss is actually good. even on less common benchmark

🤝 👍 5

2

#109 opened 22 days ago by

weijiejailbreak

Please restart openai/gpt-oss-120b endpoint + confirm logprobs support

1

#107 opened 22 days ago by

Melfarser

Model output with FP16

#106 opened 22 days ago by

AnujQCom

BEST open source 120b level model.. ever

❤️ 2

2

#104 opened 23 days ago by

DOFOFFICIAL

Multimodal support missing

#101 opened 24 days ago by

dashesy

LiveCodeBench evaluation

#100 opened 24 days ago by

wasiuddina

How to reproduce the results on hle(Humanity's Last Exam)?

#95 opened 24 days ago by

wenhanli

ImportError: /lib64/libc.so.6: version `GLIBC_2.32' not found

5

#86 opened 25 days ago by

yueqiren

Why is the performance worse on the 20B than on the 120B

2

#84 opened 25 days ago by

megabob

How to turn off thinking mode

2

#82 opened 26 days ago by

Gierry

gpt-oss120b does not actually support 131072 output tokens due to openai policies embedded limiting ouput

7

#81 opened 26 days ago by

Theodophilus

Run GPT-OSS-120B with just Single A100 (80GB)

2

#80 opened 26 days ago by

ghostplant

Please move metal/ and original/ to their own repos

➕ 2

2

#78 opened 26 days ago by

ehartford

gp-oss-120b — Exceptional Reasoning, Not Yet AGI Scale

❤️ 3

#77 opened 26 days ago by

BertrandCabotIDRIS

Qwen3 beat gpt-oss with just 0.6B with good quality enough to be usable

3

#75 opened 26 days ago by

yousef1727

Hallucinates System-promp

2

#74 opened 26 days ago by

Gradois

Can gpt-oss support local vllm deployment on a100 GPU?

10

#73 opened 26 days ago by

Cola-any

gpt_oss error when running on kaggle

2

#72 opened 27 days ago by

thehai

is this guid prompt is still valid ?

#71 opened 27 days ago by

gopi87

[Discussion] gpt-oss-120b hangs indefinitely ("thinking...") when using YaRN rope scaling to extend context length

5

#70 opened 27 days ago by

RekklesAI

Errors in chat template compared to spec

13

#69 opened 27 days ago by

zhuexe

Possible PEP 660 violation in `_build/gpt_oss_build_backend/backend.py`

#66 opened 27 days ago by

kwojciechowski

Estimated Thinking/Reasoning Token Usages For Each Modes

1

#65 opened 27 days ago by

asif00

running mxfp4 on H100 using tranformers with triton_kernel: make_default_matmul_mxfp4_w_layout not found

5

#64 opened 27 days ago by

uillliu

🚀 Best Practices for Evaluating GPT-OSS Models: Speed & Benchmark Testing Guide

🚀 ❤️ 10

1

#62 opened 27 days ago by

Yunxz

How do I serve a model in the original folder as bf16 in VLLM?

4

#60 opened 27 days ago by

bakch92

Model Performance

😔 🤗 5

1

#59 opened 27 days ago by

Joe1998

Disgusting, maximally censored model!

👍 33

16

#56 opened 27 days ago by

Lord-Kvento

🔥🔥🔥中文测评视频

#55 opened 27 days ago by

leo009

Llama, Mistral, Gemma… and now OpenAI enters the hunger games. 🐎⚔️

🚀 🔥 2

2

#54 opened 27 days ago by

Stephen555