Devstral Small 2 vs Swift 1.5 Qwen3.8-27B

Devstral Small 2 90

Memory 25, the smallest build at 4 bits from a runtime's own library is Ollama's devstral-small-2 at Q4_K_M, 15 GB, and 15 GB × 1.2 = 18 GB, within 24 GB. Mistral's own FP8 files are 25.79 GB. Runtimes 25, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the mistral3 model, llama.cpp b12242 has the architecture with a GGUF from its own organisation, and Ollama's library has devstral-small-2. Builds 10, one quantised precision from Mistral, the FP8 weights it releases. Terms 15, Apache 2.0 in the card's metadata and text, an OSI licence with nothing added. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, Mistral's own API serves Devstral Small 2: the card says the model is available through its API and points there when a local runtime underperforms. 25 + 25 + 10 + 15 + 10 + 5 = 90.

Swift 1.5 Qwen3.8-27B 80

Memory 25 of 30, UkisAI's 4-bit MLX build is 15.9 GB and its 4-bit GGUF with the vision projector 16.4 GB, both under 20 GB with a fifth added, which fits 24 GB. Runtimes 20, the architecture is Qwen3.8-27B's, which released llama.cpp, vLLM, SGLang and Transformers run, while Ollama's entry is the base's. Builds 15, GGUF, INT4, NVFP4, FP8 and MLX builds from UkisAI. Terms 10, a custom licence that is free for commercial use below US$1M revenue. Download 10, not gated. Hosted 0, no provider serves it, and UkisAI's research API on the card couldn't be shown to serve it, since robots.txt disallows calling it.

Devstral Small 2 60

File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, files in Mistral's verified mistralai organisation, which Mistral's site links to per our Mistral Large 4 listing (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or safety section, and nothing on prompt injection, instruction priority or what the model refuses. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 5, mistral.ai's security.txt gives a security contact and a submission policy, as read for the Mistral Large 4 listing (5). 25 + 15 + 0 + 0 + 15 + 5 = 60.

Swift 1.5 Qwen3.8-27B 50

File safety 25, safetensors only and nothing from the repository runs. Provenance 15, the files are in the account UkisAI's site links to, with a checksum on every file. Safety evaluation 0, none published. Agent guidance 0, nothing on prompt injection, refusals or safeguards. Licence risk 10, a revenue threshold. Security programme 0, no way to report a flaw was found.

Devstral Small 2 65

Chat template 20, chat_template.jinja in the repository (11,362 characters), with the tokenizer's tekken file for mistral-common. Tool-calling format 25, the card documents tools in the OpenAI function format with an example, names the mistral tool-call parser with auto tool choice for vLLM, shows the same for SGLang, and ships test prompts with the expected tool-call output. Trained tool calling 10, the card says the model excels at using tools, and its tests cover one tool call and calls made one at a time in sequence. Structured output 0, Nothing on the card about JSON or schema-constrained answers for this model. Reasoning control 0, no reasoning mode is documented, and a June 2026 commit removed stray thinking tokens from the files. Context 10, 256K tokens per the card, served at 262,144 in its vLLM command. 20 + 25 + 10 + 0 + 0 + 10 = 65.

Swift 1.5 Qwen3.8-27B 60

Chat template 20, the base's Jinja file. Tool-calling format 10 of 25, the format is only in the template and the parser only in serving commands. Trained tool calling 20, several calls a turn and agentic post-training. Structured output 0, not documented. Reasoning control 0, the card mentions reasoning_effort but not how to set it, turn thinking off or read the reasoning. Context 10, 262,144 tokens native.