MiMo-V2.6 Distill Qwen 9B vs Step 3.7 Flash

MiMo-V2.6 Distill Qwen 9B 65

File safety 25, safetensors only and no repository code runs. Provenance 15, the files are in Xiaomi's MiMo organisation, which mimo.xiaomi.com links to, with a checksum on every file. Safety evaluation 0, the technical report has no safety results. Agent guidance 5, the card's Use Restrictions section (28 October 2026) gives general cautions, with nothing on prompt injection, refusals or safeguards. Licence risk 15, MIT and Apache 2.0 with no conditions, and the card says its restrictions add none. Security programme 5 of 10, Xiaomi's company security centre takes reports, but nothing links it to MiMo and no advisories were found.

Step 3.7 Flash 45

File safety 15, safetensors and GGUF only, no .bin, .pt or .pth files (25). Provenance 15, the files sit in the stepfun-ai organisation, which the card's StepFun platform and model page belong to (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations section and gives no guidance on prompt injection, instruction priority, refusals or safeguards. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 0, no way to report a flaw on the card, and our StepFun API listing found no security.txt, bug bounty or disclosure policy. 15 + 15 + 0 + 0 + 15 + 0 = 45.

MiMo-V2.6 Distill Qwen 9B 70

Chat template 20, a Jinja file in the repository. Tool-calling format 10 of 25, the format is only in the template and the card names no tool parser. Trained tool calling 20, several calls a turn and agentic fine-tuning. Structured output 0, not documented. Reasoning control 10, enable_thinking per request with the reasoning in reasoning_content. Context 10, 262,144 tokens from the base's native length, though the card doesn't say.

Step 3.7 Flash 85

Chat template 20, chat_template.jinja in the repository (5,723 characters). Tool-calling format 25, the card names the parser to use in two runtimes, step3p5 in vLLM (with auto tool choice) and in SGLang, and both ship Step parsers in a release. Trained tool calling 20, the card presents tool orchestration as a main use, with multi-turn results, and the template renders every call in a turn. Structured output 0, Nothing on the card about JSON or schema-constrained output for the weights. Reasoning control 10, the template has a reasoning_effort setting and keeps reasoning_content, and the card names the step3p5 reasoning parser for vLLM and SGLang, which returns the reasoning apart from the answer. Context 10, 256K tokens per the card, and 262,144 positions in config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.

MiMo-V2.6 Distill Qwen 9B 80

Memory 30 of 30, Ollama's library build at q4_K_M is 6.6 GB, 7.9 GB with a fifth added, while Xiaomi's only build is BF16 at 18.85 GB. Runtimes 25, it keeps Qwen3.5-9B's architecture, which released vLLM, SGLang, Transformers and llama.cpp run, and Ollama's own library carries this model (entry updated 3 November 2026; the 21 October check found none). Builds 0, Xiaomi publishes no quantised build. Terms 15, MIT on the card over an Apache 2.0 base, both with nothing added. Download 10, not gated. Hosted 0, no provider serves this distill.

Step 3.7 Flash 70

Memory 5, the smallest build at 4 bits is StepFun's IQ4_XS GGUF, 104.99 GB with the 3.97 GB projector, and 108.96 GB × 1.2 = 130.8 GB, over what the reference machine can give a model and within 256 GB. The IQ3 and Q3 builds are below 4 bits and aren't read. Runtimes 20, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the step3p7 model, and llama.cpp b12242 has the architecture, with StepFun's own GGUF. Four at 5 each, and the card documents all four. Builds 15, StepFun publishes GGUF at five quantised precisions, an FP8 build and an NVFP4 build. Terms 15, Apache 2.0 in the card's metadata and its licence section, an OSI licence with nothing added. Download 10, the Hub API reports gated false for all four repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, StepFun's own API serves it, per the card and our StepFun API listing, and Featherless and DeepInfra are live for it on Hugging Face. 5 + 20 + 15 + 15 + 10 + 5 = 70.