ThoxRoute-1.5B

ThoxRoute-1.5B

Capability status (2026-09-29): Public weights. Device mapping is recorded in ttracx/thox-device-models and certified only as public + mapped + no blocked marketing claims. This is not a tok/s, AIME, or HIPAA certificate. ThoxNova names on this org are a model family, not a campaign SKU.

Your AI. Your Data. Your Rules.

Preference-routing LoRA adapter on Qwen2.5-1.5B-Instruct — a clean-room router (built to avoid the non-commercial Arch-Router license).

What this is

• Base: Qwen/Qwen2.5-1.5B-Instruct (Apache-2.0).
• LoRA r=16, α=32; task = preference/intent routing.
• Clean-room implementation — explicitly not derived from katanemo/Arch-Router (non-commercial).

Intended use

On-device / edge text generation within the THOX stack. Not a safety-aligned public assistant unless deployed behind THOX guardrails.

Prompt / chat template

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Usage

Transformers + PEFT

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = "Qwen/Qwen2.5-1.5B-Instruct"
adapter = "Thox-ai/ThoxRoute-1.5B"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
model = PeftModel.from_pretrained(model, adapter)

Links

• Base model: Qwen/Qwen2.5-1.5B-Instruct
• GGUF: Thox-ai/ThoxRoute-1.5B-GGUF
• Docs: https://docs.thox.ai

---

THOX.ai LLC — Your AI. Your Data. Your Rules. · On-device and private by design.

Temporary demo Space: tommytracx/ThoxRoute-1.5B-Space (org Space paused on quota).

<!-- THOX-STANDARD:BEGIN -->

Files

Use with ThoxOS

This repo has no GGUF. For ThoxOS / llama.cpp / Ollama / LM Studio use Thox-ai/ThoxRoute-1.5B-GGUF:

hf download Thox-ai/ThoxRoute-1.5B-GGUF --include "*.gguf" --local-dir ./ThoxRoute-1.5B-GGUF
ollama run hf.co/Thox-ai/ThoxRoute-1.5B-GGUF:Q4_K_M

Use with MeshStack

Serve the GGUF from Thox-ai/ThoxRoute-1.5B-GGUF with llama-server --host 0.0.0.0 --port 8080 (OpenAI-compatible /v1) or Ollama (:11434) and register that endpoint with your MeshStack coordinator.

To use the adapter directly: load Qwen/Qwen2.5-1.5B-Instruct with 🤗 Transformers and apply this PEFT adapter.

Device fit (by file size only)

• adapter_model.safetensors (73.91 MB): Small (<600 MB): single-board computers with ≥1 GB RAM, phones, any laptop/desktop.

RAM needed ≈ file size + context (KV cache) + runtime overhead. These tiers are derived from file size alone; no throughput, TOPS or battery figures are claimed here.

Licence and attribution

Upstream Qwen/Qwen2.5-1.5B-Instruct is Apache-2.0 (© Alibaba Cloud / Qwen team; verified against upstream Hub metadata 2026-10-23). The Apache-2.0 licence and NOTICE carry forward.

Out of scope

• Medical, legal, financial, safety-critical or other high-stakes decisions without human review.
• Unattended control of physical devices or actuators without a confirmation step.
• Any use prohibited by the upstream licence or acceptable-use policy.

Limitations and bias

• Small and quantized models make factual mistakes and can produce confident but wrong output; verify important answers.
• Behaviour and bias reflect the training data, which is mostly English web/instruction text; quality in other languages is lower unless stated above.
• Quantization trades accuracy for size; lower-bit files degrade more.

---

THOX.ai LLC — Your AI. Your Data. Your Rules.™ · thox.ai · Contact: [email protected]

<!-- THOX-STANDARD:END -->