intel-arc repositories
Trending repositories tagged intel-arc, ranked by trending score. Updated daily.
-
1
rizagp/inferzero
arcinferzero
GitHub · C++ · 68 stars · 12 forks · +13 stars in 24 hours · Trending score 2.42
-
2
watchthelight-labs/WTLIntelGfx
Intel Xe graphics acceleration for macOS and Hackintosh: Metal and Vulkan on Iris Xe, Intel Arc and Core Ultra (Meteor Lake, Arrow Lake) iGPUs. The Linux i915 driver on XNU through FreeBSD drm-kmod, with Mesa ANV. Runs on Arrow Lake under macOS Tahoe 26 and, for a tester, on Meteor Lake under Sequoia. Still a test driver.
GitHub · Rust · 70 stars · 5 forks · 0 stars in 24 hours · Trending score 0.82
-
3
IHulkSmashI/ClawDeck
What ClawTweaks and OptiClick are on Windows, for the MSI Claw on Bazzite and SteamOS: XeSS, XeSS frame generation, low latency and FSR 4 on the XMX cores, one-tap OptiScaler per game, VRR and button fixes, power profiles. One Decky plugin.
GitHub · Python · 28 stars · 2 forks · 0 stars in 24 hours · Trending score 0.68
-
4
Red-Weasel/machx-inference-engine
C++/SYCL local LLM inference for Intel Arc: Qwen3.8, DeepSeek-V4.1, MiMo-V2.6, GLM-5.3 and LTX-2.5 text-to-video on Arc Pro B70 cards. XMX kernels, quantized models, multi-GPU.
GitHub · C++ · 13 stars · 3 forks · +1 stars in 24 hours · Trending score 0.63
-
5
ProjectPhysX/OpenCL-Wrapper
OpenCL is the most powerful programming language ever created. Yet the OpenCL C++ bindings are cumbersome and the code overhead prevents many people from getting started. I created this lightweight OpenCL-Wrapper to greatly simplify OpenCL software development with C++ while keeping functionality and performance.
GitHub · C++ · 485 stars · 47 forks · 0 stars in 24 hours · Trending score 0.36
-
6
SergiioB/intel-arc-pro-b70-inference-cookbook
Pinned Intel Arc Pro B60/B70 inference recipes, engine patches and measurement records: Qwen3.8-27B EXL3 on one card (262,144 context, 63 tok/s; MTP3 measured lossy on 27% of a fixed 329-item set), Nemotron Bolt 74B, Flash-Next, dual-card routes, and a machine-checked catalog where each speculative row states whether the drafter changes the answer.
GitHub · Python · 199 stars · 13 forks · 0 stars in 24 hours · Trending score 0.35
-
7
Jumbomuffin777/XeMaya
Native inference for Intel Arc GPUs (SYCL / Level Zero, XMX): Qwen3.8-Flash-Next, GLM-5.3-Flash and DeepSeek-V4.1-Flash. Alpha. A fork of XeStrata, targeting Project Maya's models.
GitHub · C++ · 15 stars · 4 forks · 0 stars in 24 hours · Trending score 0.31
-
8
marfrit/arcint
Intel Arc LLM inference server (A770/B60): Qwen hybrids up to Qwen3.8-Flash-Next (512-expert MoE through an expert cache in VRAM and host RAM) on llama.cpp with arcint's own OpenCL kernels, MTP speculation, context checkpoints; image generation, vision, speech in and out
GitHub · C++ · 28 stars · 4 forks · 0 stars in 24 hours · Trending score 0.23
-
9
phonology024/babelscribe
Free offline speech-to-text & subtitles (SRT/VTT) in 99 languages on any GPU — AMD, NVIDIA, Intel, Apple. Whisper via whisper.cpp + MCP server for Claude, Codex, Gemini CLI.
GitHub · Python · 9 stars · 5 forks · 0 stars in 24 hours · Trending score 0.16
-
10
offbyonebit/arc-llama
Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible API.
GitHub · Python · 20 stars · 1 forks · 0 stars in 24 hours · Trending score 0.09
-
11
sortedcord/kokorolake
Kokoro-82M text-to-speech for Intel Core Ultra (Arrow Lake): hand-written XMX kernels on the Arc iGPU, Rust LSTMs, ~80 ms to first audio at 0.26 J per second of speech.
GitHub · Python · 8 stars · 0 forks · 0 stars in 24 hours · Trending score 0.09
-
12
HuskerMinion/wakesmith
Forge your own wake word: train openWakeWord & microWakeWord models from synthetic speech plus your own recordings, on Intel Arc, NVIDIA or CPU
GitHub · Python · 19 stars · 3 forks · 0 stars in 24 hours · Trending score 0.08
-
13
RodBurlamaqui/Intel-ARC-Rebar
Resizable BAR for GPUs on firmware without ReBAR support — boot-time fix + diagnostics, no firmware mod (Debian, Ubuntu, Arch, Fedora/RHEL, openSUSE packages)
GitHub · Shell · 58 stars · 6 forks · 0 stars in 24 hours · Trending score 0.06
-
14
Blackwood416/Aila
An inference engine built with SYCL + oneDNN
GitHub · C++ · 33 stars · 3 forks · 0 stars in 24 hours · Trending score 0.00
-
15
ProjectPhysX/hw-smi
A minimal, cross-compatible CPU/GPU telemetry monitor with accurate data directly from vendor APIs and beautiful ASCII visualization.
GitHub · C++ · 326 stars · 25 forks · 0 stars in 24 hours · Trending score 0.00
-
16
loblawbob873-svg/posterchanai
PosterChan AI is a Nostr-powered personal cloud and a self-hosted AI powerhouse, running on one box you own.
GitHub · Python · 27 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00
-
17
YamsSE/Arc-Power
Arc Power is a lightweight Tuning and Management Software for Intel Arc GPUs. It is powered by IGCL, RTSS, LibreHardware Monitor and OBS.
GitHub · JavaScript · 48 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00
-
18
snailium/llama.cpp-sycl-intel-b70
Community-maintained llama.cpp SYCL Docker optimized for Intel Arc Pro B70 (Battlemage). Latest oneAPI/compute-runtime/IGC, B70-specific AOT build, all features enabled (Flash Attention, MTP, reorder kernels, no GGML_SYCL_DISABLE_OPT).
GitHub · C++ · 11 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00
-
19
Uzbekunknown/dlss-nr-on-intel
Now you can run DLSS 5 NR on Intel Arc GPU. Code only. No NVIDIA binaries, no weights.
GitHub · Python · 78 stars · 10 forks · 0 stars in 24 hours · Trending score 0.00
-
20
geladons/DLSS5_INTEL
Fan research project: the real DLSS 5 (71-block DLSSNR) neural-rendering graph running live on Intel Arc via Vulkan cooperative-matrix (XMX) cores — Vulkan / DX9 / DX10 / DX11 / DX12 games + screen mode. Demo build.
GitHub · C++ · 10 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
21
skipzx-lab/precision-5820-arc-b60-large-bar
Fix small BAR / 'Resizable BAR not detected' for Intel Arc Pro B60 on Dell Precision 5820 (Purley/C422): one hidden BIOS setting, MMIO High Granularity 1G -> 64G
GitHub · Shell · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
22
DARK-Shadw/ltx25-igpu-streaming
Run the full unquantized LTX-2.5 (22B) video+audio model on a laptop's integrated GPU by streaming weights from NVMe
GitHub · Python · 5 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00
-
23
edgeduelistdisplay/local-ai-gpu-readiness-checker
Windows utility focused on gpu compatibility, local AI hardware check, and vram check for local AI workflows.
GitHub · CSS · 20 stars · 7 forks · 0 stars in 24 hours · Trending score 0.00