ThinkingCap (Qwen3.8 27B)

# Fix list: ThinkingCap (Qwen3.8 27B)

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/thinkingcap-qwen3-8-27b, the October 2026 research run, assessed 21 October 2026. Grade C, 61 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on ThinkingCap (Qwen3.8 27B): work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Risk, 45 out of 100, up to 16.9 more on the total

Why it scored 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.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-risk):

What could go wrong when you run it, and what the publisher has done about it. A higher score means less risk.

- 0 to 25, file safety. 25 for weights in safetensors or GGUF only, 15 when pickle files (.bin, .pt, .pth) sit beside them, 0 for pickle only. 10 off when the documented way to load it or to build its prompts runs code from the repository (`trust_remote_code`, or the publisher's scripts in place of a template).
- 0 to 15, provenance. 10 when the files come from the publisher's own organisation, the one its site or docs link to, and 5 for a checksum on every file.
- 0 to 20, safety evaluation. 20 when results are published and someone other than the publisher ran them or can rerun them, 10 for the publisher's own results, 0 for none.
- 0 to 15, guidance for agent use. 15 for documented prompt-injection guidance or an instruction hierarchy the model was trained to follow, 10 for a statement of what its trained refusals cover and the safeguards to add around it, 5 for general cautions, 0 for none.
- 0 to 15, licence risk. 15 to start, 5 off for each of these, a use policy or field-of-use limits beyond the law, terms the licensor can change or revoke, a revenue or user threshold, and a licence that changed without a dated note or whose link is broken. Not below 0.
- 0 to 10, a security programme. 5 for a way to report a flaw (security.txt, a disclosure policy or a security contact), 5 for advisories handled in public.

When our reference-machine runs start, measured robustness (prompt injection with AgentDojo, over-refusal with XSTest) joins Risk.

## 2. Reach, 75 out of 100, up to 9.6 more on the total

Why it scored 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.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reach):

Whether an agent can run it, and where.

- 0 to 30, memory. The smallest build from the publisher or a runtime's own library that keeps 4-bit precision or better, at its file size plus a fifth for the runtime and a working context. 30 for 16 GB or less, 25 for 24 GB, 20 for 32 GB, 15 for 64 GB, 10 for what fits our reference machine (the GPU share of 128 GB of unified memory), 5 for 256 GB, 0 above.
- 0 to 25, runtimes. 5 for each of llama.cpp, Ollama, vLLM, SGLang, LM Studio and Hugging Face Transformers that runs the architecture in a released version, from the runtime's own code, library or documentation. A publisher's fork or an unreleased branch doesn't count. 25 at most.
- 0 to 15, builds from the publisher. 15 for quantised builds at two precisions or more (FP8, 4-bit, GGUF), 10 for one, 0 when only other people's quantisations exist.
- 0 to 15, terms of use. 15 for an OSI-approved licence with nothing added, 10 for a custom licence that lets anyone use it commercially for free below a threshold or under a use policy, 5 for research or non-commercial use only, 0 for no licence or unclear terms.
- 0 to 10, download. 10 when the files download with no account and no terms to accept, 5 for a click-through that needs an account, 0 when a person approves each request.
- 5, hosted too. The publisher's own API serves it, or at least two inference providers do, so an agent without the hardware can still call it.

When our reference-machine runs start, speed on that machine (tokens per second and time to first token at the build that fits) joins Reach.

## 3. Documentation and upkeep, 53 out of 100, up to 7.2 more on the total

Why it scored 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, the repository changed on 6 October 2026. Responsiveness 10, BottleCap answered 3 of 7 discussions on the main repository. Version policy 5, the earlier ThinkingCap stays in its own repository without a dated note. File health 10, the readable metadata and builds agree and no broken-file report waits.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-upkeep):

- 0 to 20, the model card. Intended use, limitations, architecture, parameters, context length, languages and knowledge cut-off. 20 for all seven, 3 off for each that's missing.
- 0 to 20, training data. 20 for the data published or listed with sources and sizes, 15 for a data card that names the sources or the mix, the cut-off and the filtering, 10 for a general description with a cut-off, 5 without one, 0 for none.
- 0 to 20, the last change to the files, the template or the reference code. 20 within 30 days, 15 within 90, 10 within 180, 5 within a year, 0 older.
- 0 to 20, responsiveness. The publisher's replies to the 40 most recent questions and reports in the repository's discussions or issues. 20 for most, 10 for some, 5 for a few, 0 for none.
- 0 to 10, version policy. 10 for earlier versions kept in their own repositories with a dated note when one is replaced, 5 for earlier versions kept without notes or a first release, 0 when files were replaced in place without a note.
- 0 to 10, file health. 10 when config, tokenizer, template and card agree and no report of a broken file waits without a reply, 5 when one does, 0 when the files contradict the card.

## 4. Agent interface, 70 out of 100, up to 4.6 more on the total

Why it scored 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.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-interface):

What a model and a developer need to talk to it. Speech, image and other models with no chat interface read the tool-calling and structured-output lines for what the model takes and returns (voices, timestamps, streaming, typed outputs), and the note says how.

- 0 to 20, the chat template. 20 for a template in the repository (Jinja, in the tokenizer config or its own file), 10 when the prompt format is only given as code you run.
- 0 to 25, the tool-calling format. 25 when the publisher documents how tools are declared and how calls come back, with the parser to use in a named runtime, 10 when only the template or a runtime's own recipe says it.
- 0 to 20, tool calling the model was trained for. 20 with several calls in one turn, 10 for one call at a time.
- 0 to 15, structured output. 15 when JSON or JSON Schema output is documented for the model with how to ask for it, 5 when the card claims it without saying how.
- 10, reasoning control. Thinking that can be turned off or budgeted per request, with where the reasoning text comes back.
- 0 to 10, context. 10 for 128K tokens or more trained, 5 for 32K to 127K. Context reached only by scaling the position encoding counts one band down.

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- Download was read on the repository graded, which is gated (5). BottleCap's GGUF, NVFP4 and MLX builds aren't gated, so reading the line on the builds would give 10 and Reach 80
- unchecked, a SHA-256 for every file in the gated repository, since the Hub hides LFS hashes until the gate is accepted. If they're there, provenance is 15 and Risk 50
- unchecked, what the 6 October 2026 change to the main repository was and whether LICENSE ever changed, since the commit history is gated
- Responsiveness counts the main repository only (3 of 7). Counting the GGUF repository too gives 10 of 14, which reads as most and 20
- The GGUF cards carry the gate's request form in their metadata while the repositories aren't gated, so BottleCap may gate them later

## Weaknesses

- PolyForm Small Business licence, free commercially only below 100 people and 1,000,000 USD (2019) revenue
- The BF16 and FP8 repositories are gated behind contact details
- No safety results, agent guidance, security contact or training-data description
- No hosted API or inference provider
- Every accuracy and token-saving figure comes from BottleCap's own harness

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Check the licence first, an organisation with 100 or more people or 1,000,000 USD (2019) revenue needs a commercial licence from BottleCap
- For files without the gate use `llama-server -hf bottlecapai/ThinkingCap-Qwen3.8-27B-GGUF:Q4_K_M --jinja`, about 17.4 GB
- On vLLM use `--reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_xml`, and on SGLang `--tool-call-parser qwen3_coder`
- Set `reasoning_effort` (xhigh, medium or low) in chat_template_kwargs, any other value makes the template raise an error
- Keep the base's sampling (temperature 1.0, top_p 0.95, top_k 20), the GGUF card says greedy decoding can loop
- The GGUFs carry an MTP head, and llama.cpp builds without MTP support for this architecture may refuse to load them with a missing blk.64 tensor

## What the review panel asked for

- publish a changelog outside the gate
- a published commercial licence price
- independent benchmark submissions
- a security contact
- publish safety results

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.