gpt-oss-20b vs Ornith-1.5-122B

gpt-oss-20b 85

File safety earns 25, since the weights are safetensors and metal/model.bin is OpenAI's own raw Metal format rather than pickle, and nothing in the repository runs as code (a judgement call on the .bin name). Provenance earns 15, files in OpenAI's own organisation and a checksum on every file. Safety evaluation earns 10, because the published safety results for this size are OpenAI's own, and the outside review covered gpt-oss-120b. Agent guidance earns 15 for an instruction hierarchy the model was trained to follow, with prompt-injection results, though OpenAI reports it trails o4-mini there. Licence risk keeps 15, with nothing to deduct under Apache 2.0. The security programme earns 5 for OpenAI's security.txt with a Bugcrowd contact. Public advisories for the gpt-oss code couldn't be checked, so that half scores as absent.

Ornith-1.5-122B 50

File safety 25, safetensors and GGUF only and no Python in any of Ornith's repositories for this size, so the card's --trust-remote-code flag loads nothing from the repository. Provenance 15, the files come from the ornith-ai organisation Ornith's blog links to, with a SHA-256 for every weight file. Safety evaluation 0 and agent guidance 0, nothing published on either. Licence risk 10, MIT carries no policy, threshold or changeable terms, but the card's licence link is broken. Security programme 0, no security.txt, disclosure policy or security contact.

gpt-oss-20b 90

Memory earns 25, since OpenAI's own MXFP4 build is 13.76 GB and a fifth on top is 16.5 GB, just past the 16 GB band, and Ollama's 14 GB build lands in the same 24 GB band. Runtimes earn the full 25 from model code in released Transformers, vLLM and SGLang, the architecture in llama.cpp and the model in Ollama's library. Builds earn 10, because OpenAI ships one quantised precision, MXFP4, and the original and metal folders are the same weights for its reference code. Terms earn 15 for Apache 2.0, whose usage policy only asks users to follow the law. Download earns 10, since the repository isn't gated. Hosted earns 5, with five inference providers live for it on its Hugging Face page on 1 November 2026, while OpenAI's own API lists it with no usable rate limit and isn't counted.

Ornith-1.5-122B 75

Memory 10, since Ornith's own MLX 4-bit build is 69.7 GB and needs about 83.6 GB with the fifth added, over 64 GB and inside the reference machine's 107.4 GB, as do its Q4_K_M GGUF, its NVFP4 build and Ollama's build. Runtimes 25, the most the line gives, from vLLM 0.33.0, SGLang 0.5.23, Transformers 5.22.2, llama.cpp's qwen35moe architecture, Ollama's library and LM Studio's catalogue for the qwen35moe architecture. Builds 15, Ornith publishes FP8, NVFP4, GGUF and MLX at several precisions. Terms 15, MIT as named in the card's metadata, with nothing added, read by its terms though the repository has no licence file. Download 10, nothing is gated. Hosted 0, Ornith runs no API and no inference provider serves it. 10 + 25 + 15 + 15 + 10 + 0 = 75.

gpt-oss-20b 42

The model card earns 17, covering six of the seven points and missing a statement of supported languages. Training data earns 10, a general description with a June 2024 cut-off and no sources or mix. Last change earns 5, because the files haven't changed since August 2025 and the reference code and harmony parser last changed on 1 and 5 November 2025, still within a year on 1 November 2026, while this year's commits only touch the browser tool, CI and a version number. Responsiveness earns 0, with no OpenAI reply to any of the 40 most recent discussions and none at all since August 2025. Version policy earns 5 for a first release kept in its own repository. File health earns 5, since template reports and an install report wait without a reply.

Ornith-1.5-122B 36

Model card 11, it covers intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off. Training data 5, a description of the method with no data or cut-off. Last change 20, a folder upload to the MLX builds on 24 October 2026, 17 days ago. Responsiveness 0, Ornith answered none of the 5 questions and reports. Version policy 0, the MLX builds were uploaded a second time four days after the first with no note. File health 0, the card links a missing LICENSE, states hardware its own files don't fit and names a variant that doesn't exist, and the two chat templates differ. 11 + 5 + 20 + 0 + 0 + 0 = 36.

gpt-oss-20b 90

The chat template earns 20, a Jinja file in the repository. The tool-calling format earns 25, since OpenAI's harmony guide says how functions are declared and how calls come back, and OpenAI ships the openai-harmony parser. Trained tool calling earns 10, because each call ends the message and waits for its result, so it makes one call at a time. Structured output earns 15 for a JSON Schema given in the developer message, documented in the harmony guide. Reasoning control earns 10, with low, medium or high effort per request and the reasoning on its own channel, though it can't be switched off. Context earns 10 for 131,072 tokens, which OpenAI describes as trained in even though the config reaches it with YaRN.

Ornith-1.5-122B 85

Chat template 20, a Jinja file in the repository. Tool-calling format 25, the card shows how tools go in and how calls come back and names the parser for vLLM and SGLang. Trained tool calling 20, Ornith trains it on agent tasks and the template renders several calls in one turn. Structured output 0, not documented or claimed. Reasoning control 10, Ornith's template reads enable_thinking per request and the card says the reasoning comes back in reasoning_content, though the card doesn't name the switch. Context 10, 262,144 tokens native.