Ling-3.1-flash-1019 vs MiniCPM-V 4.7 35B-A3B

Ling-3.1-flash-1019 60

Memory 0, inclusionAI's only build is the FP8 release at 573.78 GB, × 1.2 = 688.5 GB, above 256 GB, and no runtime's library has a build. Runtimes 25, Released model code in Transformers 5.22.2 (bailing_hybrid), vLLM 0.33.0 (BailingMoeV3ForCausalLM, with ling3 tool and reasoning parsers), SGLang 0.5.23 (bailing_moe_v3.py, its bailing_hybrid config and MTP module) and llama.cpp b12242 (bailingmoe3), and Ollama, credited through its pinned llama.cpp as on the Ling-3.0-tiny listing: v0.40.16 sets LLAMA_CPP_VERSION to b12177. Builds 10, the release is FP8, the one quantised precision inclusionAI publishes for it. Terms 15, MIT in the card's metadata, with no use policy or other terms added on the card or in the repository. Download 10, the Hub API's model info gives gated false on 10 November 2026, so the files download with no account and no terms to accept. Hosted 0, the Hub API's provider mapping is empty for this repository on 10 November 2026. 0 + 25 + 10 + 15 + 10 + 0 = 60.

MiniCPM-V 4.7 35B-A3B 90

Memory 25, since OpenBMB's IQ4_XS GGUF with its vision projector is 19.6 GB and needs about 23.6 GB with the fifth added, which fits 24 GB, while its Q4_K_M GGUF, 4-bit safetensors builds and Ollama entry need 32 GB. Runtimes 25, from vLLM 0.33.0, SGLang 0.5.23, Transformers 5.18.0 and later, llama.cpp's own MiniCPM-V 4.7 support and OpenBMB's entry on Ollama. Builds 15, OpenBMB publishes FP8, three 4-bit safetensors builds and GGUF. Terms 15, Apache 2.0 with nothing added. Download 10, nothing is gated. Hosted 0, no inference provider is mapped. 25 + 25 + 15 + 15 + 10 + 0 = 90.

Ling-3.1-flash-1019 56

Model card 11, Intended use (complex reasoning, multi-step tasks and agentic workflows), architecture, parameters (560B total, 25B active) and context (1M claimed) are on the card. Training data 15, the training-content summary the card links names the source categories (Common Crawl and other public datasets, commercially licensed data, the Ant Spider crawler, synthetic data), the size band (over 10 trillion text tokens), data collected up to about July 2026 and the filtering, without listing datasets with sizes. Last change 20, the newest commit, on 4 November 2026, edited the card, six days before this check, and the files went up on 27 October. Responsiveness 0, Neither of the 2 discussions that aren't pull requests (both opened on 27 October 2026) has a reply from an inclusionAI member. Version policy 5, the update went into a repository of its own and Ling-3.1-flash and Ling 3.0 stay in theirs. File health 5, the card states a 1M-token context while config.json gives 262,144 with no rope scaling, and its serve commands name the earlier repository as the model path. 11 + 15 + 20 + 0 + 5 + 5 = 56.

MiniCPM-V 4.7 35B-A3B 68

Model card 8, it covers intended use, architecture and parameters but not limitations, context length, languages or a knowledge cut-off. Training data 0, none described. Last change 20, a commit on 3 November 2026. Responsiveness 20, OpenBMB answered 8 of 12 discussions. Version policy 10, earlier versions keep their repositories and the changes are dated and described. File health 10, the files agree. 8 + 0 + 20 + 20 + 10 + 10 = 68.

Ling-3.1-flash-1019 45

File safety 15, safetensors only, no .bin, .pt or .pth files (25), less 10 because the card's documented vLLM command passes --trust-remote-code, which runs the repository's configuration_bailing_moe_v3.py, since vLLM 0.33.0 registers no bailing_hybrid config of its own. Provenance 15, files in the inclusionAI organisation that inclusion-ai.org links to, per the Ling-3.0-tiny listing (10). Safety evaluation 0, no safety results for the model on its card or in the training-content summary. Agent guidance 0, the card has nothing on prompt injection, refusals or safeguards, and inclusionAI publishes no guardrail probe for this model as it did for Ling 3.0. Licence risk 15, MIT with no use policy, no field-of-use limits, no threshold and no clause letting inclusionAI change or revoke it. Security programme 0, www.inclusion-ai.org answers 404 for security.txt on 10 November 2026, and the Ling-3.0-tiny listing found no SECURITY.md or disclosure policy in the inclusionAI .github repository. 15 + 15 + 0 + 0 + 15 + 0 = 45.

MiniCPM-V 4.7 35B-A3B 55

File safety 25, safetensors and GGUF only, no Python in the main repository and no remote code needed. Provenance 15, the files come from the openbmb organisation OpenBMB's GitHub README links to, with a SHA-256 for every weight file. Safety evaluation 0 and agent guidance 0, nothing published on either, and the card has no limitations section. Licence risk 15, plain Apache 2.0. Security programme 0, no security.txt or SECURITY.md.

Ling-3.1-flash-1019 60

Chat template 20, chat_template.jinja in the repository (6,042 characters), which handles tools, the thinking switch and preserved reasoning. Tool-calling format 10, only the template says how tools are declared (JSON in <tools>) and how calls come back (<tool_call>name with <arg_key> and <arg_value> pairs). Trained tool calling 20, the template tells the model it may call one or more functions and loops over every entry in an assistant message's tool_calls, and the card reports gains on agentic benchmarks, AA-Briefcase and AutomationBench-AA among them. Structured output 0, the card doesn't document JSON or JSON Schema output. Reasoning control 0, the card documents turning thinking on or off per request with chat_template_kwargs enable_thinking, and names the ling3 reasoning parser, but doesn't say where the reasoning text comes back. Context 10, 262,144 tokens natively in config.json (max_position_embeddings 262144, rope_scaling null) and per SGLang's cookbook. 20 + 10 + 20 + 0 + 0 + 10 = 60.

MiniCPM-V 4.7 35B-A3B 70

Chat template 20, a Jinja file in the repository. Tool-calling format 10, the card shows the tools array going in but not the call coming back, and names no parser. Trained tool calling 20, the template renders several calls in one turn. Structured output 0, not documented or claimed. Reasoning control 10, enable_thinking per request, off by default, with the trace between markers. Context 10, 262,144 tokens native.