gpuos

Chat · Pro plan

Run Aya Expanse 8B · Q8_0 on your own GPU

Aya Expanse 8B · Q8_0 is a chat catalog model (8.0B) managed with Ollama. Catalog memory is estimated at 11 GB with Q8_0 for a short context (4–8K tokens). Validate output quality and memory use with your workload on your hardware.

Deploy the catalog Ollama tag on your machine and verify the pulled model's quantization. Once deployed, gpuos serves it as aya-expanse-8b-q8-0 through the hosted gpuos gateway, with API keys, optional token quotas and usage metering. Request and response payloads pass through that gateway.

Parameters
8.0B
Quantization
Q8_0
Est. VRAM (4–8K ctx)
≈ 11 GB
Catalog context
8K tokens
License
Noncommercial terms
Engine
Ollama
Ollama tag
aya-expanse:8b-q8_0
API
/v1/chat/completions

This model has noncommercial restrictions. Review the publisher's terms.

Compare GPU memory for Aya Expanse 8B · Q8_0

Catalog estimate at Q8_0, not a measured benchmark. Chat estimates assume a short context; embedding memory depends on input and batch size. The comparison includes a 5% screening margin; it does not establish runtime performance. More in how much VRAM an LLM needs.

Check this estimate against your GPU with the VRAM calculator

Call Aya Expanse 8B · Q8_0 with the OpenAI SDK

Use the supported chat completions endpoint with your gpuos base URL, API key and deployed model id. Validate any model-specific features your app needs. Setup for LangChain, Continue, Open WebUI and more is in integrations.

Python
from openai import OpenAI

client = OpenAI(base_url="https://gpuos.si/v1", api_key="gpuos_key_…")
stream = client.chat.completions.create(
    model="aya-expanse-8b-q8-0",
    messages=[{"role": "user", "content": "Summarize our refund policy."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")
Node.js
import OpenAI from "openai"

const client = new OpenAI({ baseURL: "https://gpuos.si/v1", apiKey: process.env.GPUOS_API_KEY })
const reply = await client.chat.completions.create({
  model: "aya-expanse-8b-q8-0",
  messages: [{ role: "user", content: "Summarize our refund policy." }],
})
console.log(reply.choices[0].message.content)
curl
curl https://gpuos.si/v1/chat/completions \
  -H "Authorization: Bearer $GPUOS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "aya-expanse-8b-q8-0", "messages": [{"role": "user", "content": "Hello"}]}'

Questions

How much VRAM does Aya Expanse 8B · Q8_0 need?
The catalog estimate is 11 GB at Q8_0 for a short context (4–8K tokens). The RTX 4070 Ti Super 16 GB clears this estimate with screening headroom in the comparison list. This is a planning estimate, not a tested hardware requirement. Validate context length, batch size and concurrent requests on your node.
Can I use Aya Expanse 8B · Q8_0 commercially?
Aya Expanse 8B · Q8_0 is released under the Noncommercial terms. This model has noncommercial restrictions. Review the publisher's terms.
Is Aya Expanse 8B · Q8_0 compatible with the OpenAI API?
Through gpuos, Aya Expanse 8B · Q8_0 uses the supported /v1/chat/completions endpoint with the model id "aya-expanse-8b-q8-0". Configure your OpenAI-compatible client with the gpuos base URL and API key. Check model-specific features and any other API operations your app needs before switching.
Which gpuos plan includes Aya Expanse 8B · Q8_0?
Aya Expanse 8B · Q8_0 is part of the full catalog on the Pro plan, $29 per GPU per month.

Related models

Plan your Aya Expanse 8B · Q8_0 deployment with gpuOS

Create a free workspace and follow the quickstart to connect a node. Start with a Community model, or upgrade inside your workspace for the full catalog.

Start freeRead the quickstart