Devstral Small 2 vs ThinkingCap (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.

ThinkingCap (Qwen3.8 27B) 75

Memory 25 of 30, BottleCap's IQ4_XS GGUF is 15.5 GB, 18.6 GB with a fifth added, which fits 24 GB. Runtimes 20, it keeps the base's qwen3_5 architecture, which llama.cpp, vLLM, SGLang and Transformers run in released versions, while Ollama's entry is the base's. Builds 15, FP8, NVFP4, MLX and GGUF from BottleCap. Terms 10, PolyForm Small Business is free commercially only below 100 people and 1,000,000 USD (2019) revenue. Download 5, the main repository is gated behind a click-through with an account and contact details, though the GGUF, NVFP4 and MLX builds aren't. Hosted 0, no API or inference provider serves 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.

ThinkingCap (Qwen3.8 27B) 45

File safety 25, safetensors only and no code in the repository. Provenance 10 of 15, the files are in BottleCap's verified organisation, but the Hub hides the gated files' SHA-256 from the public, so checksums couldn't be confirmed. Safety evaluation 0, none published. Agent guidance 0. Licence risk 10, 5 off for the size and revenue threshold. Security programme 0, no security.txt, disclosure policy or security contact.

Devstral Small 2 46

Model card 11, Intended use, the architecture, the parameters and the context are on the card. Training data 0, Nothing on the card about the training data. Last change 10, the last commit, on 15 July 2026, updated the files to match mistral-common, 118 days before this check and within 180. Responsiveness 10, Of the 23 most recent discussions that aren't pull requests (9 December 2025 to 6 November 2026), 11 have a reply from a mistralai member, which is some. Version policy 5, Devstral Small 1.1 stays in its own repository, which this card links as the predecessor, with no dated note on the older card that we read. File health 10, Config, template, tokenizer and card agree, and the June and July commits fixed stray tokens and brought the files in line with mistral-common. 11 + 0 + 10 + 10 + 5 + 10 = 46.

ThinkingCap (Qwen3.8 27B) 53

Model card 8 of 20, intended use, limitations and parameters are there, but architecture, context, languages and a cut-off aren't. Training data 0, not described. Last change 20, BottleCap's GGUF build of the model changed its card on 7 October 2026, 27 days ago. Responsiveness 10, BottleCap answered 4 of 8 discussions on the main repository. Version policy 5, the earlier ThinkingCap stays in its own repository with an undated pointer to this one. File health 10, the readable metadata and builds agree and no broken-file report waits.

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.

ThinkingCap (Qwen3.8 27B) 70

Chat template 20, the same Jinja template as Qwen3.8-27B, in the repository. Tool-calling format 10 of 25, the card names the parsers but the format lives only in the template. Trained tool calling 20, several calls a turn, and BottleCap evaluated agent tasks. Structured output 0, not documented. Reasoning control 10, reasoning_effort budgets thinking per request and the card says where the reasoning comes back. Context 10, 262,144 tokens.