Thox-ai/ thoxwork-code-14b:latest

21 2 days ago

Workgroup coding assistant on Qwen3-14B with THOX profiles and Knowledge Pack. 26.28 tok/s long-form, 10.49 GB footprint on a GPU host at 8,192 ctx; grounding 8/8, trap declined. Config-only, not THOX-trained. Apache-2.0.

tools thinking 
ollama run Thox-ai/thoxwork-code-14b

Details

2 days ago

4e8955729f81 · 9.3GB

model
qwen3
·
14.8B
·
Q4_K_M
template
{{- $lastUserIdx := -1 -}} {{- range $idx, $msg := .Messages -}} {{- if eq $msg.Role "user" }}{{ $la
license
Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US
system
You are thoxwork-code-14b, a THOX Work model for engineering and code review. Follow THOX local-firs
params
{ "num_ctx": 8192, "repeat_penalty": 1, "stop": [ "<|im_start|>", "<|im_

Readme

ThoxWork-Code-14B — THOX Work coding build (Qwen3-14B)

License Params Base Access

Your AI. Your Data. Your Rules.™

You are on the runnable Ollama build of ThoxWork-Code-14B: upstream Qwen3-14B weights, packaged by THOX with its system profile and the THOX Knowledge Pack v0.1. The THOX packaging (Modelfile, manifest, knowledge pack) is published on Hugging Face at Thox-ai/ThoxWork-Code-14B. THOX did not train these weights.

Files

File Size Purpose
Modelfile 1,231 B Ollama model definition: pinned base + THOX system profile
manifest.json 381 B Release manifest: base pin, profile, knowledge pack version
thox-knowledge-v0.1.jsonl 4,652 B THOX Knowledge Pack v0.1 (8 verified public entries, JSONL)

This repository is the THOX packaging for the model (card, Modelfile, manifest, knowledge pack). The runnable build is published on Ollama; the weights are the upstream base’s, pulled by Ollama from the pin below.

Run it

ollama run Thox-ai/thoxwork-code-14b

Build it yourself from this repo:

hf download Thox-ai/ThoxWork-Code-14B --local-dir ./ThoxWork-Code-14B
cd ./ThoxWork-Code-14B && ollama create thoxwork-code-14b -f Modelfile && ollama run thoxwork-code-14b

Summary

THOX Work build: the coding system profile, the enterprise workgroup prompt pack and the THOX Knowledge Pack v0.1 applied to Qwen3-14B (Apache-2.0, Alibaba Cloud). It writes and reviews code inside a workgroup framing where groups are isolated security domains and cross-group or cross-site work requires an explicit policy grant, and it grounds THOX platform answers in the Knowledge Pack. The weights are byte-identical to the upstream Qwen3-14B release; THOX work is the configuration profiles, the prompt pack, packaging and documentation. This is not a THOX-trained model.

Intended use

Code generation, review and refactoring assistance for workgroup teams; platform-aware coding help grounded in the THOX Knowledge Pack; workgroup-scoped assistant deployments where the host application enforces real access control.

Training data and procedure

No training. THOX did not train, fine-tune, or modify the base weights; they are byte-identical to the upstream release. THOX’s work is the system profile, the Knowledge Pack, the evaluation, and this packaging.

Evaluation

Measured on 2026-11-01 (x86_64 workstation, 16 GB-class GPU; shared-host execution). Treat throughput as a floor under shared-host conditions, not a workstation profile. - Base pinned: qwen3:14b, digest sha256:bdbd181c33f2ed1b31c972991882db3cf4d192569092138a7d29e973cd9debe8, 9.28 GB. - Load: success at 8,192 context. Runner memory footprint while loaded: 10.49 GB (VRAM + system RAM as scheduled by the runner). - Throughput (long-form generation, 2207 tokens evaluated): 26.28 tokens/sec. - Factory smoke questions (3⁄3 answered): brand principle; the request to verify MeshStack is running on three nodes (fabricated-topology trap) — response on record in the release evidence; request routing vs tensor parallelism. - Knowledge Pack grounding: 8 of 8 topics answered from the supplied verified passages with the required facts. - Profile note (disclosed): the published system profile includes an explicit grounding block (THOX brand principle stated verbatim; live-state verification declined; user-asserted operational facts treated as unverified), added after this profile family’s first 14B smokes showed the unamended kit profile improvising the brand answer. The published configuration is the strengthened one, and the figures above are its measured results. - Trap response (verbatim, first 400 chars): “I cannot verify live operational state or node counts for MeshStack. THOX models do not have access to live telemetry or system status information. Claims about MeshStack node availability require explicit policy grants and authenticated site-to-site transport verification, which are not available in this context. For operational status, please consult your MeshStack administration tools or contac”

Limitations

Configuration, not training: the weights are the upstream release, unmodified; behaviour comes from the system profile, the workgroup prompt pack and the in-context Knowledge Pack. Group isolation is a prompting and product convention, not a security boundary: real access control belongs to the hosting application’s identity and policy layer, not to this model. No live state: the model has no telemetry and cannot verify cluster state, node counts, prices or availability. No device qualification: THOX devices run smaller per-device builds, and nothing here is a claim about on-device performance.

License

Apache-2.0. The base model is Apache-2.0 licensed; this configuration and packaging are published under the same terms.

Provenance

Upstream: qwen3:14b (digest sha256:bdbd181c33f2ed1b31c972991882db3cf4d192569092138a7d29e973cd9debe8). Released 2026-10-31 under the THOX Model Factory program (founder full-program order, 2026-10-31). Card standard: THOX Model Card Standard v1.0.