This article details how the author successfully ran OpenAI's Codex CLI against a gpt-oss:120b model hosted on an NVIDIA DGX Spark, accessed through a Tailscale network. It covers the setup of Tailscale, Ollama configuration, and the process of running the Codex CLI with the remote model, including building a Space Invaders game.
A detailed guide for running the new gpt-oss models locally with the best performance using `llama.cpp`. The guide covers a wide range of hardware configurations and provides CLI argument explanations and benchmarks for Apple Silicon devices.
oLLM is a Python library for running large-context Transformers on NVIDIA GPUs by offloading weights and KV-cache to SSDs. It supports models like Llama-3, GPT-OSS-20B, and Qwen3-Next-80B, enabling up to 100K tokens of context on 8-10 GB GPUs without quantization.
An in-depth look at the architecture of OpenAI's GPT-OSS models, detailing tokenization, embeddings, transformer blocks, Mixture of Experts, attention mechanisms (GQA and RoPE), and quantization techniques.
A user shares their experience running the GPT-OSS 120b model on Ollama with an i7 6700, 64GB DDR4 RAM, RTX 3090, and a 1TB SSD. They note slow initial token generation but acceptable performance overall, highlighting it's possible on a relatively modest setup. The discussion includes comparisons to other hardware configurations, optimization techniques (llama.cpp), and the model's quality.
>I have a 3090 with 64gb ddr4 3200 RAM and am getting around 50 t/s prompt processing speed and 15 t/s generation speed using the following:
>
>`llama-server -m <path to gpt-oss-120b> --ctx-size 32768 --temp 1.0 --top-p 1.0 --jinja -ub 2048 -b 2048 -ngl 99 -fa 'on' --n-cpu-moe 24`
> This about fills up my VRAM and RAM almost entirely. For more wiggle room for other applications use `--n-cpu-moe 26`.
>I have a 3090 with 64gb ddr4 3200 RAM and am getting around 50 t/s prompt processing speed and 15 t/s generation speed using the following:
>
>`llama-server -m <path to gpt-oss-120b> --ctx-size 32768 --temp 1.0 --top-p 1.0 --jinja -ub 2048 -b 2048 -ngl 99 -fa 'on' --n-cpu-moe 24`
> This about fills up my VRAM and RAM almost entirely. For more wiggle room for other applications use `--n-cpu-moe 26`.
This blog post details a fine-tuning workflow for the gpt-oss model that recovers post-training accuracy while retaining the performance benefits of FP4. It involves supervised fine-tuning (SFT) on an upcasted BF16 version of the model, followed by quantization-aware training (QAT) using NVIDIA TensorRT Model Optimizer. The article also discusses the benefits of using NVFP4 for even better convergence and accuracy recovery.
OpenAI's release of GPT-OSS marks their first major open source LLM since GPT-2, featuring improvements in reasoning, tool usage, and problem-solving capabilities. The article explores its architecture, message formatting, reasoning modes, and tokenizer details.
A user demonstrates how to run a 120B model efficiently on hardware with only 8GB VRAM by offloading MOE layers to CPU and keeping only attention layers on GPU, achieving high performance with minimal VRAM usage.
OpenAI releases gpt-oss-120b and gpt-oss-20b, two state-of-the-art open-weight language models that deliver strong real-world performance at low cost. They outperform similarly sized open models on reasoning tasks and are optimized for efficient deployment.
