RUNLOCALAIv38
→WILL IT RUNBEST GPUCOMPARETROUBLESHOOTSTARTPULSEMODELSHARDWARETOOLSBENCH
RUNLOCALAI

Operator-grade instrument for local-AI hardware intelligence. Hand-written verdicts. Real benchmarks. Reproducible commands.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
  • Will it run?
GUIDES
  • Best GPU
  • Best laptop
  • Best Mac
  • Best used GPU
  • Best budget GPU
  • Best GPU for Ollama
  • Best GPU for SD
  • AI PC build $2K
  • CUDA vs ROCm
  • 16 vs 24 GB
  • Compare hardware
  • Custom compare
REF
  • Systems
  • Ecosystem maps
  • Pillar guides
  • Methodology
  • Glossary
  • Errors KB
  • Troubleshooting
  • Resources
  • Public API
EDITOR
  • About
  • About the author
  • Changelog
  • Latest
  • Updates
  • Submit benchmark
  • Send feedback
  • Trust
  • Editorial policy
  • How we make money
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

SYS · ONLINEUPTIME · 100%2026 · operator-owned
RUNLOCALAI · v38
  1. >
  2. Home
  3. /Tools
  4. /DirectML
runner
free (Windows-bundled)

DirectML

Microsoft's DirectX 12 inference backend. The Windows-native path for AMD / Intel / Qualcomm GPU + NPU acceleration without ROCm or vendor-specific SDKs. Used through ONNX Runtime as the DML execution provider.

By Fredoline Eruo·Last verified May 7, 2026·2,400 GitHub stars

Overview

Microsoft's DirectX 12 inference backend. The Windows-native path for AMD / Intel / Qualcomm GPU + NPU acceleration without ROCm or vendor-specific SDKs. Used through ONNX Runtime as the DML execution provider.

Pros

  • Vendor-agnostic on Windows — same code path runs on AMD / Intel / Qualcomm
  • No CUDA / ROCm install required — DirectX 12 is pre-installed on Windows 10+
  • First-class Snapdragon X Elite + Lunar Lake NPU support via DML drivers

Cons

  • Windows-only — no Linux / macOS path
  • Throughput trails CUDA + native ROCm by 15-30%
  • LLM-specific optimizations behind vLLM / llama.cpp

Compatibility

Operating systems
Windows
GPU backends
NVIDIA
AMD
Intel
Qualcomm
LicenseClosed source · free (Windows-bundled)

Runtime health

Operator-grade signals on how actively DirectML is being maintained, how fresh its measurements are, and what failure classes operators have flagged. Every label below is anchored to a real date or count — we never infer maintainer activity we can't show.

Release cadence

Derived from the most recent editorial signal on this row.

Active
Updated May 7, 2026

6 days since last refresh · source: lastUpdated

Benchmark freshness

How recent the editorial measurements on this runtime are.

0editorial benchmarks

No editorial benchmarks for this runtime yet.

Community reproduction

Submissions that match an editorial measurement on similar hardware.

0reproduced reports

No community reproductions on file yet.

Get DirectML

Official site
https://learn.microsoft.com/en-us/windows/ai/directml/dml
GitHub
https://github.com/microsoft/DirectML

Frequently asked

Is DirectML free?

DirectML has a paid tier (free (Windows-bundled)). Check the pricing page for current terms.

What operating systems does DirectML support?

DirectML supports Windows.

Which GPUs work with DirectML?

DirectML supports NVIDIA, AMD, Intel, Qualcomm. CPU-only inference is also possible but slow.
See something off?Report outdated·Suggest a correctionWe read every submission. Editorial review takes 1-7 days.

Reviewed by RunLocalAI Editorial. See our editorial policy for how we evaluate tools.

Related — keep moving

Compare hardware
  • RTX 3090 vs RTX 4090 →
  • Apple M4 Max vs RTX 4090 →
Buyer guides
  • Best GPU for local AI →
  • Best budget GPU →
When it doesn't work
  • llama.cpp too slow →
  • llama.cpp build failed →
  • llama.cpp Metal crash (Mac) →
  • GGUF tokenizer mismatch →
Recommended hardware
  • RTX 3090 (used) →
  • Apple M4 Max →
Alternatives
MLX-LMExLlamaV2llama.cppLlamafileOllamaIPEX-LLMCTranslate2Intel OpenVINO
Before you buy

Verify DirectML runs on your specific hardware before committing money.

Will it run on my hardware? →Custom hardware comparison →GPU recommender (4 questions) →