GLM-4.7-Flash vs OTel-2.0-LLM-31B-IT

GLM-4.7-Flash 28

The card covers architecture, parameters and languages and misses four of the seven items, for 8. Training data is 0, as the card describes none. The last change was on 1 February 2026 at the latest, within a year but past 180 days, for 5. Responsiveness is 5, since zai-org answered 6 of the 40 most recent discussions, all by 31 January, which is a few. Version policy is 5 for a first release with no files replaced, and file health is 5, as config.json and tokenizer_config.json disagree on context and a config report waits without a reply.

OTel-2.0-LLM-31B-IT 74

Model card 14, Intended use, a long limitations section, the architecture and training method, the parameters (31B) and the language (English) are on the card. Training data 15, the card names the sources (3GPP, ETSI, ITU, GSMA, CAMARA, O-RAN and TM Forum material provided by GSMA), the overall sizes (15 billion raw tokens, over 1 trillion processed, about 440 billion used), the mix of example types and the processing tool, and lists what was left out. Last change 20, the last commit, on 1 November 2026, updated the card's links, resources, citation and contacts, nine days before this check. Responsiveness 20, Of the 3 discussions that aren't pull requests (7 August to 28 October 2026), 2 have a reply from the repository's owner, which is most. Version policy 0, the weights were replaced in place: uploads on 27 July, 3 August and 1 September 2026 under one name, with a standing notice on the card that they may change and that users should pin a revision, and no dated note of what changed. File health 5, the card describes 15 shards of about 62.6 GB while the repository still holds an earlier 14-shard set beside them, 126.8 GB in all. 14 + 15 + 20 + 20 + 0 + 5 = 74.

GLM-4.7-Flash 80

Memory earns 25, since Ollama's smallest build is the 19 GB q4_K_M one, about 22.8 GB with the fifth added, which fits 24 GB. Runtimes reach the cap of 25, with model code in released vLLM, SGLang and Transformers, a converter in a released llama.cpp build and a local entry in Ollama's library. Builds earn nothing, because Z.ai publishes only BF16 and every quantised build is someone else's. The MIT licence with nothing added gives the full 15 for terms, the files download with no account or gate for 10, and Z.ai plus three other providers serve it for 5.

OTel-2.0-LLM-31B-IT 50

Memory 10, the publisher's only build is the BF16 safetensors, 62.55 GB for the 15 shards the index names, and 62.55 GB × 1.2 = 75.1 GB, above 64 GB and inside the reference machine's GPU share. Runtimes 15, the architecture is Gemma4ForConditionalGeneration, which vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 run from the safetensors files, three at 5 each. Builds 0, the publisher ships the BF16 weights only. Terms 15, Apache 2.0 in the card's metadata, an OSI licence, with nothing added on the card. Download 10, gated is false on 10 November 2026, so the files download with no account or terms. Hosted 0, Hugging Face maps one inference provider, Featherless AI (live), short of the two the line needs. 10 + 15 + 0 + 15 + 10 + 0 = 50.

GLM-4.7-Flash 85

A Jinja chat template sits in the repository, for 20. The tool-calling format is the full 25, because Z.ai itself names the glm47 parser for vLLM and SGLang, says tools are declared in OpenAI style and shows calls coming back as tool_calls. The template takes several calls in one turn, for 20. Structured output is 0, with nothing on the card and only the hosted API documented for JSON. Reasoning control is 10, thinking turned off per request with enable_thinking and the reasoning returned by the glm45 parser. Context is 10, 202,752 positions native with no rope scaling.

OTel-2.0-LLM-31B-IT 60

Chat template 20, chat_template.jinja in the repository, 19,300 characters, the publisher's own. Tool-calling format 10, only the template says how tools are declared and how calls come back. Trained tool calling 20, the template loops over tool_calls, so it renders several calls in one turn, and the card says the training mix included general-purpose agentic tool-calling examples, while none were specific to telecoms. Structured output 0, the card doesn't document JSON or JSON Schema output. Reasoning control 0, the card says the model wasn't trained to produce or consume Gemma's thought channel and answers directly, so there is no thinking to switch or budget. Context 10, 262,144 positions in the text config, the base's native context. 20 + 10 + 20 + 0 + 0 + 10 = 60.