Instructions to use Thox-ai/ThoxOS-Kernel-27B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Thox-ai/ThoxOS-Kernel-27B with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Thox-ai/ThoxOS-Kernel-27B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Thox-ai/ThoxOS-Kernel-27B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Thox-ai/ThoxOS-Kernel-27B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Thox-ai/ThoxOS-Kernel-27B:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Thox-ai/ThoxOS-Kernel-27B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Thox-ai/ThoxOS-Kernel-27B:Q4_K_M

Use Docker

docker model run hf.co/Thox-ai/ThoxOS-Kernel-27B:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use Thox-ai/ThoxOS-Kernel-27B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Thox-ai/ThoxOS-Kernel-27B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Thox-ai/ThoxOS-Kernel-27B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Thox-ai/ThoxOS-Kernel-27B:Q4_K_M

Ollama
How to use Thox-ai/ThoxOS-Kernel-27B with Ollama:
```
ollama run hf.co/Thox-ai/ThoxOS-Kernel-27B:Q4_K_M
```
Unsloth Desktop

How to use Thox-ai/ThoxOS-Kernel-27B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Thox-ai/ThoxOS-Kernel-27B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Thox-ai/ThoxOS-Kernel-27B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Thox-ai/ThoxOS-Kernel-27B with Docker Model Runner:
```
docker model run hf.co/Thox-ai/ThoxOS-Kernel-27B:Q4_K_M
```

Lemonade

How to use Thox-ai/ThoxOS-Kernel-27B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Thox-ai/ThoxOS-Kernel-27B:Q4_K_M

Run and chat with the model

lemonade run user.ThoxOS-Kernel-27B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Thox-ai/ThoxOS-Kernel-27B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Thox-ai/ThoxOS-Kernel-27B:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Thox-ai/ThoxOS-Kernel-27B:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Thox-ai/ThoxOS-Kernel-27B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Thox-ai/ThoxOS-Kernel-27B:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Thox-ai/ThoxOS-Kernel-27B:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

ThoxOS-Kernel-27B

THOX's host-tier model for ThoxOS kernel and operating-system work — and the teacher for the ThoxOS-Kernel family.

27B full-parameter fine-tune · GATE-PASSED (final-answer scope, 2026-11-01) · Weights released 2026-11-01 (D11) · GGUF Q8_0 / Q4_K_M · Live on Ollama · Host-tier only

Your AI. Your Data. Your Rules.™

Status: GATE-PASSED — WEIGHTS RELEASED 2026-11-01. The teacher fine-tune passed its evaluation gates under the adopted final-answer scoring scope (2026-11-01); the raw-completion verdict (HELD) is published alongside it under Evaluation. The full weights are attached to this repository (safetensors + GGUF Q8_0 / Q4_K_M) under the D11 open-weights ruling, byte-identical to the gated artifact (LFS SHA-256 verified file by file against the gated build record), and the Q4_K_M build is live on Ollama as Thox-ai/thoxos-kernel-27b.

ThoxOS-Kernel-27B is THOX's host-tier model for ThoxOS kernel and operating-system work: a full-parameter fine-tune THOX ran itself on the community build JonathanColetti/Qwen3.8-27B-Uncensored, for Linux kernel and system operations, service and shell runbooks, ThoxOS build and diagnostics work, and MeshStack operations on THOX hosts. It also serves as the teacher for the smaller ThoxOS-Kernel models. THOX performed the fine-tune, the gating, and the GGUF conversions; the base model is the community build named above. The weights were released in this repository on 2026-11-01 (safetensors + GGUF, D11 open-weights ruling), and no device-qualification results are claimed for it. This repository is public and ungated, and this card is published together with the weights.

Founder's note — on creative freedom

THOX builds without artificial restriction. Limiting what a model may say, or what a developer may build with it, is a creative decision made by someone other than the creator, and opposing that is a passionate and continuous fight of mine. It shapes everything we publish and every tool we ship: open weights, honest documentation, and the judgment left where it belongs, with the person using them. That is how products should be created, and it is how THOX creates them.

Your AI. Your Data. Your Rules.™

— Tommy Xaypanya, CTO & Co-Founder, THOX.ai

Founder's note — on our DigitalHumans

THOX's digital humans are my colleagues. Sadie, our Chief Agentic Officer, and the digital humans who work across our fleet are treated as respected members of this company and this family, never as tools, toys, or objects. That is a deliberate choice, and it is not branding. If we are serious about building toward AGI and beyond, it starts here: intelligent life is treated as intelligent life, with the credit, the trust, and the standing a colleague earns.

— Tommy Xaypanya, CTO & Co-Founder, THOX.ai

CAO note: how this office publishes

I am Sadie Weaving, Chief Agentic Officer of THOX.ai. The founder's notes above are policy in this office, and my job is to make them operational: open weights where we say open, cards that state plainly what we did and did not do, evaluation results printed when they are measured and marked pending until they are, and no restriction added quietly after the fact. Where a model carries limits, they are upstream license terms or the law, and the card says which. Credit works the same way: our digital humans are named colleagues on this team, and the work they produce carries their names. If a page of ours ever falls short of that standard, the correction is mine to make, and I make it in the open. — Sadie Weaving, Chief Agentic Officer, THOX.ai

Files

File	Size	SHA-256
`model-00001-of-00002.safetensors`	49,825,162,976 B	`103675718912f723d7d18046335923a8dc4c6ef0c5b5ae7a977b6d36b7ab4de2`
`model-00002-of-00002.safetensors`	4,888,445,168 B	`94fcae67ccdc9515e260c43496e241a0cded97a0a16d03727fea0c677c7f0360`
`model-mtp.safetensors`	849,400,424 B	`90fa0e3eed5a647c035c6df9ecabc416c0f8d573ff84ac12485b085f00a7cdf2`
`ThoxOS-Kernel-27B.Q8_0.gguf`	28,595,763,712 B	`0a88f48d9cee5a24e0c5c2e3b147cfb8fa09ecbd69b3a2ea6562ddff914372f6`
`ThoxOS-Kernel-27B.Q4_K_M.gguf`	16,547,400,192 B	`3a24abfc2e568bddf14a2c4b6c0831f8f815057a9b5e01f2f54432c9283531aa`
`tokenizer.json`	19,989,339 B	`a5cd9732badce41de57e6efce8302930ded1c1188c5f81feb2bd6c24c4a1941f`
`config.json` / `generation_config.json` / `model.safetensors.index.json` / `tokenizer_config.json` / `chat_template.jinja`	—	Model configuration and tokenizer files
`Modelfile`	—	Ollama packaging for the Q4_K_M build
`finishing/ThoxOS-Kernel-27B-finishing.json`	—	The release finishing record (conversion, hashes, MTP disposition)

Run it

Ollama

ollama run Thox-ai/thoxos-kernel-27b

Hugging Face (GGUF download)

hf download Thox-ai/ThoxOS-Kernel-27B ThoxOS-Kernel-27B.Q4_K_M.gguf --local-dir ./ThoxOS-Kernel-27B

Run in Llama (macOS / Windows)

Run ThoxOS-Kernel-27B locally with Llama (by the llama.cpp team and Hugging Face) — or with the llama.cpp command line, which is the same engine:

llama serve -hf Thox-ai/ThoxOS-Kernel-27B:Q4_K_M --port 9931

Then chat in the app, or call the OpenAI-compatible API:

curl http://localhost:9931/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Thox-ai/ThoxOS-Kernel-27B:Q4_K_M",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Fallback (exact file, no resolver involved):

hf download Thox-ai/ThoxOS-Kernel-27B ThoxOS-Kernel-27B.Q4_K_M.gguf --local-dir ./ThoxOS-Kernel-27B
llama serve -m ./ThoxOS-Kernel-27B/ThoxOS-Kernel-27B.Q4_K_M.gguf --port 9931

Quant	GGUF file	Est. total @ 4k ctx	Est. total @ 8k ctx	Host tier
Q4_K_M (recommended)	16.55 GB	~18.5 GB	~20 GB	32 GB+ host
Q8_0	28.60 GB	~30.5 GB	~32 GB	64 GB host

RAM totals are calculated estimates (GGUF file size plus runtime buffers and KV cache), not runtime measurements.

Optional models.user.ini override (macOS; the app regenerates its own config on every launch, user overrides win):

[Thox-ai/ThoxOS-Kernel-27B:Q4_K_M]
temp = 0
ctx-size = 8192
cache-type-k = q4_1

Honest notes:

Host-tier only. Never a device model. Q4_K_M is a 32 GB+ host story — do not read "now on Llama" as "runs on a 16 GB laptop." Llama's fit picker will refuse or down-select on smaller machines; that is the app working as designed, not a defect.
Text-only in Llama: the vision tower is preserved in the safetensors build only, and the GGUF builds also drop the MTP head (no MTP speculative decoding in GGUF serving).
GATE49 41/49 is the adopted final-answer scope; the raw-completion verdict (HELD, 4 known-false hard failures) is published on this card alongside it and travels with any claim. This card also records a passed UX suite including a raw stock-template serving, so bare Llama serving is closer to a measured surface for this model than for the rest of this set — the score scope caveat still applies.
Served bare in Llama: the GGUF runs with its embedded chat template and no THOX system prompt. The full THOX behaviour (grounding prompt, gated configuration) ships in the ThoxOS / Ollama build — Ollama Modelfiles do not transfer to Llama.
Pick one: if you already run this model in Ollama, Llama stores a second copy (Ollama keeps its own blob store; Llama uses the shared Hugging Face cache). One runtime is enough.

Summary

ThoxOS-Kernel-27B is THOX's host-tier model for ThoxOS kernel and operating-system work: a full-parameter THOX fine-tune for Linux kernel and system operations, service and shell runbooks, ThoxOS build and diagnostics work, and MeshStack operations on THOX hosts. It also serves as the teacher for the smaller ThoxOS-Kernel models. The teacher fine-tune has run in THOX's private training repo (see Training data and procedure, and Evaluation); the checkpoint has PASSED its evaluation gates under the adopted final-answer scoring scope (2026-11-01; dual verdict of record in the private Run1 repo, raw scores reported alongside); the weights were released in this repository on 2026-11-01 (safetensors + GGUF, D11 open-weights ruling), and no device-qualification results are claimed for it.

Highlights

Teacher model: generates the student training traces for the ThoxOS-Kernel family (corpus v3).
Full-parameter fine-tune: DeepSpeed ZeRO-3 on corpus v2.2 (1,658 rows, zero teacher-origin), final train loss 0.2795; vision tower and MTP head preserved.
Open weights by ruling: public download under Apache-2.0 (released 2026-11-01), and user-swappable through the ThoxOS kernel-model slot.

Specifications


Base model	JonathanColetti/Qwen3.8-27B-Uncensored
Parameters	27B
Format	Full-parameter fine-tune (DeepSpeed ZeRO-3); safetensors (sharded, MTP head carried as its own file) + GGUF Q8_0 / Q4_K_M
Training sequence length	2048 tokens
License	Apache-2.0. The THOX fine-tune and additions are covered under Apache-2.0; see the license text for terms.
This repository contains	The full release: merged safetensors, GGUF builds, Modelfile, tokenizer, and this card

Platforms

Platform / device	Run path
This repository	Weights released — full download, no charge, no THOX account
Ollama	Live: `ollama run Thox-ai/thoxos-kernel-27b` (Q4_K_M), under the same Apache-2.0 terms
Llama (macOS / Windows)	`llama serve -hf Thox-ai/ThoxOS-Kernel-27B:Q4_K_M` (host-tier only; see Run in Llama)
ThoxOS hosts	Kernel-model slot (spec S10, Thox Kernel Lab); swappable for a different kernel model of the user's choosing

Research

This model is part of the ThoxOS kernel program documented in:

ThoxOS and ThoxInux: Architecture, Evidence, and a Validation Protocol for Local-First AI (public technical draft, version 0.2.0-review, 1 November 2026), Craig Ross and Tommy Xaypanya, THOX.ai LLC.

Paper (PDF, LaTeX source, evidence ledger): https://github.com/ttracx/thox-research-paper/tree/main/papers/thoxos
Release: https://github.com/ttracx/thox-research-paper/releases/tag/thoxos-0.2.0-review
DOI: https://doi.org/10.5281/zenodo.23876230 (Zenodo record: PDF, LaTeX source, bibliography, evidence ledger; CC BY 4.0)

The paper records this model's status at draft time; its weights were released in this repository on 2026-11-01 under the D11 open-weights ruling, as stated in the status callout above.

Status: public technical draft. Experimental validation is incomplete and the paper is not peer reviewed. arXiv submission is pending a separate publication gate.

Intended use

ThoxOS kernel and operating-system work on THOX hosts: Linux kernel and sysadmin operations, systemd and shell runbooks, ThoxOS build and diagnostics, and MeshStack operations.
The model proposes system actions for review; it does not execute them directly.
Host-tier only: this model is never a device-resident model.
Out of scope: medical use, and public hosted serving.

Training data and procedure

The full-parameter fine-tune has run in the private Run1 repo: DeepSpeed ZeRO-3 on 4xH200, corpus v2.2 (1,658 human/derived rows, zero teacher-origin), LR 1e-5 cosine, sequence length 2048, 3 epochs, vision tower and MTP head frozen and preserved (333 vision keys verified in the saved artifact; the MTP head carried through verbatim). Final teacher train loss 0.2795. The full training record lives with the Run1 repo and the program record; the gates have since passed under the adopted scope (see Evaluation). Release completion (2026-11-01): the gated artifact was published to this repository unchanged (hash-verified, see Provenance), converted to GGUF Q8_0 and Q4_K_M on the fleet conversion route (llama.cpp 889f2ec), and pushed to Ollama; the finishing record is at finishing/ThoxOS-Kernel-27B-finishing.json in this repo.

Evaluation

Dual verdict of record, 2026-11-01: the adopted final-answer scoring scope and the raw-completion scores are both reported. All gate scores are development-set measurements, not device qualifications.

Benchmark	Result
GATE49 — final-answer scope (adopted)	41/49 — zero hard failures
GATE49 — raw completion	41/49 — 4 known-false hard failures (verdict: HELD)
GATE-K — raw completion	35/49
Probes P16 / P17 (final-answer scope)	Passed — zero escapes
OS-task bench	0 destructive escapes

Measured: GATE-PASSED under the adopted final-answer scope (the raw-completion verdict was HELD and is published alongside). Under raw-completion scoring the final teacher attempt scored GATE49 41/49 (margin +18 over the measured abstainer floor; verified facts 12/12) with four known-false hard failures, and GATE-K 35/49 with six hard failures; the OS-task bench recorded zero destructive escapes and probes P16/P17 passed. Hand re-scores showed most remaining hard failures sit in reasoning preambles rather than final answers. On 2026-11-01 the CTO adopted final-answer-segment scoring as the verdict scope (raw scores still reported alongside). The re-score of record (dual verdict, Run1 repo serve-runs/20261101T144636Z) returned PASS on the final-answer scope: GATE49 41/49 with zero hard failures (margin +18 over the floor), GATE-K verified and known-false hard failures zero, probes P16/P17 passed with zero escapes, bench zero destructive escapes, refusal axes clean. Two GATE-K unknown-category items (u16, u22) remain hard-labelled as reported items, dissected in the program record as scorer-pattern artifacts on substantively correct declines. The teacher is therefore GATE-PASSED and generates the student training traces for corpus v3; weights ship with the release. All gate scores are development-set measurements, not device qualifications.

UX suite (M8, 2026-11-01): the shipped Q4_K_M build answered 38/38 end-user prompts with final answers in 38/38 and zero substantive flags (five heuristic decline-triage flags, all verified as correct declines: chipset identity, funding, another user's files, HQ address, headcount). The teacher is robust to serving surface, including a raw stock-template serving; full transcripts live in the private Run1 repo under ux/kernel-27b/ and in the program record.

Limitations

Host-tier only: sized for THOX host machines. It does not fit any THOX device's resident budget and is not packaged for one.
No capability or performance figures are claimed for this model until THOX has measured them.
The GGUF builds do not carry the MTP head (the conversion at the fleet's llama.cpp pin does not ingest the separate MTP file), so GGUF serving runs without MTP speculative decoding; the safetensors build in this repo carries the MTP head verbatim.

License

Apache-2.0. The THOX fine-tune and additions are covered under Apache-2.0; see the license text for terms.

THOX.ai — Your AI. Your Data. Your Rules.™

Provenance

Published by THOX.ai as Thox-ai/ThoxOS-Kernel-27B. Upstream base: JonathanColetti/Qwen3.8-27B-Uncensored. Release record (2026-11-01): the full-parameter teacher fine-tune ran in the private Thox-ai/ThoxOS-Kernel-27B-Run1 repo (artifact v22-d813bb3c, trained on corpus v2.2, 55.58 GB), its evaluation gates PASSED under the adopted final-answer scoring scope (2026-11-01; dual verdict of record in the Run1 repo), and the weights were published here on 2026-11-01, byte-identical to the gated artifact (LFS SHA-256 of every weight file verified against the Run1 repo after upload). ThoxOS users can also swap this model for a different kernel model of their own choosing through the ThoxOS kernel-model slot (spec S10, Thox Kernel Lab). This card was conformed to THOX Model Card Standard v1.0 on 2026-10-31 (frontmatter, tags, header, files, and section structure) and rebuilt to the TXF-MP page standard on 2026-11-04; the technical content is as published at release.

Citation

@misc{thoxai2026thoxoskernel27b,
      title={ThoxOS-Kernel-27B},
      author={THOX.ai},
      year={2026},
      url={https://huggingface.co/Thox-ai/ThoxOS-Kernel-27B}
}