TinkerLab
ARTIFACT // DOCKER-COMPOSE.ARC-B60-RDNA4.YML (YAML)

Intel Arc Pro B60 (24GB/48GB) & AMD RX 9070 XT (RDNA 4) Vulkan/ROCm Compose Stack (docker-compose.arc-b60-rdna4.yml)

Production Docker Compose stack passing /dev/dri with numeric render GID, Vulkan multi-GPU device selection, and Q8_0 KV Cache for Intel Arc Pro B60 24GB and AMD Radeon RX 9070 XT 16GB.

[KEY VERIFIED TAKEAWAY / TL;DR]This reproducible configuration artifact "Intel Arc Pro B60 (24GB/48GB) & AMD RX 9070 XT (RDNA 4) Vulkan/ROCm Compose Stack" (docker-compose.arc-b60-rdna4.yml, YAML) is paired with Tinker AI Lab's hardware-verified guide "intel-arc-pro-b60-24gb-vs-radeon-rx-9070-xt-rdna4-rocm-vulkan-benchmark". It exposes 3 customizable browser variables (HOST_RENDER_GID=109, VK_DEVICES=0, BIND_PORT=11434) with loopback-first security defaults.
01 // HOMELABLocal AI / HomeLab· Verified: 2026-10-28
Browse All 42 Artifacts →
docker-compose.arc-b60-rdna4.yml

Intel Arc Pro B60 (24GB/48GB) & AMD RX 9070 XT (RDNA 4) Vulkan/ROCm Compose Stack

Production Docker Compose stack passing /dev/dri with numeric render GID, Vulkan multi-GPU device selection, and Q8_0 KV Cache for Intel Arc Pro B60 24GB and AMD Radeon RX 9070 XT 16GB.

View Paired Guide →
Customizable Variables (Saved in Browser)
UTF-8 Encoded · Live Client-Side Compilation
# Tinker AI — Intel Arc Pro B60 (24GB/48GB) & AMD RX 9070 XT (RDNA 4) Stack (Guide #27)
services:
  ollama-vulkan:
    image: ollama/ollama:0.6.2
    container_name: tinker-b60-rdna4-llm
    restart: unless-stopped
    ports:
      - "127.0.0.1:11434:11434"
    devices:
      - /dev/dri:/dev/dri
    group_add:
      - "109"
    environment:
      - GGML_VK_VISIBLE_DEVICES=0
      - OLLAMA_FLASH_ATTENTION=1
      - OLLAMA_KV_CACHE_TYPE=q8_0
      - OLLAMA_NUM_PARALLEL=2
      - OLLAMA_KEEP_ALIVE=30m
    volumes:
      - ./ollama-data:/root/.ollama
PARAMETER SPECIFICATION // 参数化变量规范说明表

Customizable Parameter Reference for docker-compose.arc-b60-rdna4.yml

This YAML artifact exposes 3 template variables compiled client-side in your browser.

Template TokenParameter DescriptionVerified DefaultExample Format
{{HOST_RENDER_GID}}Host /dev/dri/renderD128 Numeric GID109109 (Run: stat -c "%g" /dev/dri/renderD128)
{{VK_DEVICES}}Vulkan Visible GPU Indices00 (Single GPU) or 0,1 (Dual Arc Pro B60 48GB)
{{BIND_PORT}}Host Loopback Port1143411434
PAIRED HARDWARE MANIFEST // 配套实测环境与边界记录

Verified Environment for "Budget High-VRAM Homelab Showdown: Intel Arc Pro B60 (24GB / Dual 48GB) vs AMD Radeon RX 9070 XT (16GB RDNA 4) on Vulkan & ROCm 6.3.4"

Tested Hardware & OS

2x Intel Arc Pro B60 (24GB GDDR6 · 456 GB/s · 160 XMX each) & AMD Radeon RX 9070 XT (16GB GDDR6 · 640 GB/s · gfx1201) · Linux Kernel 6.13.5 · Ubuntu 24.04.2 LTS

Pinned Stack & Model Versions
Linux Kernel 6.13.5 (Intel xe + amdgpu)Mesa 25.0.2 (ANV & RADV Vulkan)ROCm 6.3.4 (Native gfx1201)llama.cpp b4910 (Vulkan & HIP Backends)
Offline Boundary (100% Air-Gapped Capable)

Runs via local `/dev/dri` Vulkan or ROCm containers bound strictly to `127.0.0.1:11434`.

Known Operational Limits & Failure Modes
  • Intel Arc Pro B60 (24GB) has a 192-bit bus (456 GB/s): it fits 32B Q4_K_M models that OOM on 16GB cards, but its raw memory bandwidth is ~29% lower than RX 9070 XT (640 GB/s) on 14B models.
  • On AMD RX 9070 XT (`gfx1201`), setting legacy `HSA_OVERRIDE_GFX_VERSION=11.0.0` crashes ROCm immediately; use native `gfx1201` in ROCm 6.3.4+ or Mesa 25.0+ RADV Vulkan.
DEPLOYMENT CHECKLIST // 配置落地核验步骤

3-Step Verification Checklist After Deploying docker-compose.arc-b60-rdna4.yml

  1. Confirmed Linux Kernel >= 6.13 and Mesa >= 25.0 so Intel `xe` (BMG-G21) and AMD `gfx1201` (RDNA 4) bind natively.
  2. Verified `HSA_OVERRIDE_GFX_VERSION` is NOT set on AMD RX 9070 XT (`gfx1201`).
  3. Passed numeric `/dev/dri/renderD128` GID via `--group-add` and enabled `OLLAMA_KV_CACHE_TYPE=q8_0`.