openai/gpt-oss-20b · Discussions

#108 opened about 4 hours ago by

Noah0627

Added VLLM Offline Serve working code.

#107 opened about 5 hours ago by

hrithiksagar-tih

Update README.md

#106 opened about 15 hours ago by

Lorriea73

safe_serialization

#105 opened about 17 hours ago by

cuongdk253

347_solver_5134dccf8f test js discussion

#104 opened 1 day ago by

347_solver_5134dccf8f test iframe discussion

#103 opened 1 day ago by

347_solver_5134dccf8f test discussion 3

#102 opened 1 day ago by

347_solver_5134dccf8f test discussion

#101 opened 1 day ago by

NVIDIA L40S GPU's for MXFP4 quantization

#100 opened 1 day ago by

lordim

CUDA out of memory issues when running gptoss model on colab T4

#99 opened 1 day ago by

sumeetm

Should have a `model_type` key in its config.json

➕ 1

#98 opened 2 days ago by

Sneha7

gpt

#97 opened 2 days ago by

xaibie

gptoss

#96 opened 2 days ago by

xaibie

What is the metal/model.bin for?

#95 opened 2 days ago by

sigjhl

model quality issues

5

#92 opened 3 days ago by

TheBigBlockPC

The Abliterated version is the version we deserved.

😔 1

#91 opened 3 days ago by

Koitenshin

The censorship here is just... amazing.

👍 3

#90 opened 3 days ago by

smokeofc

Does transformers utilize PyTorch SDPA's flash_attention for openai/gpt-oss-20b?

#89 opened 3 days ago by

NooBaymax

GPT-OSS-20B.LOCAL

#88 opened 3 days ago by

recod4160

Quick Results: Testing Multilingual Capabilities via Code Generation from Ukrainian Competitive Programming Tasks

🚀 3

#87 opened 3 days ago by

anon-researcher-ua

How to turn off thinking mode

🔥 3

#86 opened 3 days ago by

Gierry

I haven't seen a more useful model than this one.

#85 opened 3 days ago by

Maria99934

How to run it on macOS

❤️ 1

6

#84 opened 3 days ago by

kopyl

There is no spark.. only darkness

#83 opened 4 days ago by

JFE

laihiujin

#81 opened 4 days ago by

laisiuin

tool calling not working as expected?

👍 1

5

#80 opened 4 days ago by

Spider-Jerusalem

SVG problem

#79 opened 4 days ago by

Alkohole

Honest Review of the Model

😎 👍 41

#78 opened 4 days ago by

MarinaraSpaghetti

behavior between GptOssExperts and Mxfp4GptOssExperts

#77 opened 4 days ago by

DaleMeng

'accelerate' missing in the model card.

#76 opened 4 days ago by

Ina-Developer

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

👀 1

#75 opened 4 days ago by

yousef1727

triton_kernels and multiprocessing

#74 opened 4 days ago by

piotrm0

Thanks for the great model

👀 2

#73 opened 4 days ago by

deniiiiiij

Running gpt-oss Without FlashAttention 3 – Any Alternatives to Ollama?

#72 opened 4 days ago by

shinho0902

getting curernt Date template issue with OLLAMA_ORIGINS="chrome-extension://*" OLLAMA_DEBUG=1 ollama serve

#71 opened 4 days ago by

lokesher

how to ignore the quantization

❤️ 👍 4

#70 opened 4 days ago by

zzbysd

Is there no usable PyTorch for Python 3.12?

#69 opened 4 days ago by

xiaotianyu2025

This is by far the worst model out there... Won't be using this. 🚮🗑️

🤯 ➕ 6

#67 opened 5 days ago by

UniversalLove333

question: setting reasoning effort

5

#66 opened 5 days ago by

TheBigBlockPC

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

❤️ 🔥 8

#64 opened 5 days ago by

Yunxz

information how to get it working on a 3090

👍 4

11

#63 opened 5 days ago by

TheBigBlockPC

It seems to be censored a bit too much.

🤯 👍 8

6

#62 opened 5 days ago by

petwoe

MXFP4 only runs on h100 or b100 or later versions,

😔 1

10

#61 opened 5 days ago by

kishan51

AIME 25 Accuracy Discrepancy for GPT-OSS-20B (Reasoning Effort=High)

#58 opened 5 days ago by

jiayi37u

🔥🔥🔥中文测评视频

#56 opened 5 days ago by

leo009

Report

🤝 1

#55 opened 5 days ago by

Mks1837

Thinking but no solution?