openai/gpt-oss-120b · Discussions

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

#125 opened about 1 hour ago by

ssfyasuo

Is this demo powered by hugging face?

👍 🤗 1

#124 opened about 3 hours ago by

terobox

Very bad censorship

#123 opened about 16 hours ago by

YesIamKurt

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

#122 opened 1 day ago by

meetzuber

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

#121 opened 1 day ago by

Byrdi

Create ابو الرشد ٢٠٢٥

#120 opened 3 days ago by

Shrif7roshdi

Update README.md

#119 opened 6 days ago by

Lorriea73

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

1

#118 opened 7 days ago by

aidenpan0x

Fine tune 120b at 8 H100s getting cuda OOM error

3

#117 opened 7 days ago by

jinxu88

68.4 on Aider Polyglot with reasoning_effort: high

🔥 2

#116 opened 7 days ago by

Fernanda24

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

#112 opened 8 days ago by

lllIIIlIlIk

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

#110 opened 9 days ago by

GazJ16

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

🤝 👍 5

2

#109 opened 9 days ago by

weijiejailbreak

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

1

#107 opened 9 days ago by

Melfarser

Model output with FP16

#106 opened 10 days ago by

AnujQCom

BEST open source 120b level model.. ever

❤️ 2

2

#104 opened 10 days ago by

DOFOFFICIAL

Multimodal support missing

#101 opened 11 days ago by

dashesy

LiveCodeBench evaluation

#100 opened 11 days ago by

wasiuddina

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

#95 opened 12 days ago by

wenhanli

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

5

#86 opened 12 days ago by

yueqiren

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

2

#84 opened 13 days ago by

megabob

How to turn off thinking mode

2

#82 opened 13 days ago by

Gierry

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

1

#81 opened 13 days ago by

Theodophilus

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

2

#80 opened 13 days ago by

ghostplant

Please move metal/ and original/ to their own repos

➕ 2

2

#78 opened 14 days ago by

ehartford

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

❤️ 3

#77 opened 14 days ago by

BertrandCabotIDRIS

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

3

#75 opened 14 days ago by

yousef1727

Hallucinates System-promp

1

#74 opened 14 days ago by

Gradois

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

10

#73 opened 14 days ago by

ustcHouHou

gpt_oss error when running on kaggle

2

#72 opened 14 days ago by

thehai

is this guid prompt is still valid ?

#71 opened 14 days ago by

gopi87

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

5

#70 opened 14 days ago by

RekklesAI

Errors in chat template compared to spec

13

#69 opened 14 days ago by

zhuexe

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

#66 opened 14 days ago by

kwojciechowski

Estimated Thinking/Reasoning Token Usages For Each Modes

1

#65 opened 14 days ago by

asif00

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

5

#64 opened 14 days ago by

uillliu

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

🚀 ❤️ 9

1

#62 opened 15 days ago by

Yunxz

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

4

#60 opened 15 days ago by

bakch92

Model Performance

😔 🤗 5

1

#59 opened 15 days ago by

Joe1998

Disgusting, maximally censored model!

👍 32

16

#56 opened 15 days ago by

Lord-Kvento

🔥🔥🔥中文测评视频

#55 opened 15 days ago by

leo009

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

🚀 🔥 2

2

#54 opened 15 days ago by

Stephen555

Request: FP8 / BF16 version of model?

👍 1

1

#53 opened 15 days ago by

Epliz

кал

➕ 👍 3

#51 opened 15 days ago by

Serg4451D

how to disable the reasoning mode?

👍 10

6

#50 opened 15 days ago by

szzzzz

Enterprise AI factory OS

#47 opened 15 days ago by

DavidSteinbauer

How to use different reasoning effort in the example?

🔥 1

1

#45 opened 15 days ago by

TianheWu

Structured Outputs

1

#44 opened 15 days ago by

DykeF

Problems with Metal

3

#42 opened 15 days ago by

Thalesian

[v1 engine][flash_attn backend] TypeError: flash_attn_varlen_func() got an unexpected keyword argument 's_aux' when running gpt-oss-120b on H200

👍 7

13

#41 opened 15 days ago by

RekklesAI