---
title: Qwen3.5-9B Q8_0 on the Radeon RX 9070 XT 16GB (Linux)
url: "https://bitworks.io/amd-inference/recipes/rx-9070-xt-16gb-linux-qwen3-5-9b-q8/"
description: Candidate Linux single-card configuration for RX 9070 XT 16 GB; no published fit or performance result.
---

# Qwen3.5-9B Q8_0 on the Radeon RX 9070 XT 16GB (Linux)

> Candidate Linux single-card configuration for RX 9070 XT 16 GB; no published fit or performance result.

Human-readable page: https://bitworks.io/amd-inference/recipes/rx-9070-xt-16gb-linux-qwen3-5-9b-q8/

## Content

- **Status:** In lab testing (candidate)

- **GPU:** 1 × AMD Radeon RX 9070 XT 16GB

- **Operating system:** Linux

- **Backend:** Not yet selected

- **Model:** Qwen3.5-9B Q8_0 — Unsloth GGUF conversion of Qwen/Qwen3.5-9B (Apache-2.0)

- **Context:** 32768 tokens

- **Concurrency:** 1

- **Placement:** full-gpu

No measured results are published for this recipe.

## Overview

This Linux candidate pairs the RX 9070 XT 16 GB with the pinned model and quantization named above at the catalog's 32,768-token context. This 9070 XT shares the 16 GB memory tier with the non-XT card but remains a distinct hardware test. The same pinned Q8 9B model can make later matched comparisons possible without implying an outcome now. It is a test plan, not a claim of load, full-GPU placement, answer quality or speed.

## Requirements

The current Linux path is a private, supervised source-checkout workflow for one recognized Vulkan GPU and a loopback server. It requires explicit artifact consent. No physical Linux AMD serving outcome is qualified. Check the card's currently reported free GPU memory, not just the number printed on its box. A longer prompt, more active requests and the desktop can change the memory budget. Keep the exact driver and operating-system build with any later test.

The pinned GGUF is 9,527,502,048 bytes (9.53 GB decimal). Keep more free local SSD space than the artifact itself for verified acquisition and cache maintenance; no fixed extra margin or host-RAM minimum has been qualified. Review the exact model license before acquisition. A planned trial must record the actual free-memory budget, selected device, loaded context, host and GPU buffers, delivered output and representative answers. The catalog context is an intended setting, not a demonstrated maximum.

For agents: how to buy here — https://bitworks.io/checkout.md