---
title: Qwen3.8-27B UD-Q4_K_M on the Radeon RX 7900 XTX 24GB (Linux)
url: "https://bitworks.io/amd-inference/recipes/rx-7900-xtx-24gb-linux-qwen3-8-27b-q4km/"
description: Candidate Linux single-card configuration for RX 7900 XTX 24 GB; no published fit or performance result.
---

# Qwen3.8-27B UD-Q4_K_M on the Radeon RX 7900 XTX 24GB (Linux)

> Candidate Linux single-card configuration for RX 7900 XTX 24 GB; no published fit or performance result.

Human-readable page: https://bitworks.io/amd-inference/recipes/rx-7900-xtx-24gb-linux-qwen3-8-27b-q4km/

## Content

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

- **GPU:** 1 × AMD Radeon RX 7900 XTX 24GB

- **Operating system:** Linux

- **Backend:** Not yet selected

- **Model:** Qwen3.8-27B UD-Q4_K_M — Unsloth GGUF conversion of Qwen/Qwen3.8-27B (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 7900 XTX 24 GB with the pinned model and quantization named above at the catalog's 32,768-token context. The 24 GB XTX candidate uses a different Q4 27B artifact and 32K catalog context than the 20 GB XT profile. Extra nominal memory permits a different proposed test, but does not prove the longer context or model placement succeeds. 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 16,464,440,224 bytes (16.46 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