Skip to content
The Daily Repo

uncSoft / anubis-oss

Local LLM Testing & Benchmarking for Apple Silicon

Why this job: says: local llm; topics: apple-silicon, ollama, local-llm, inference, mlx

What it does

  • Select any model from any configured backend
  • Stream responses with live metrics overlay
  • 8 metric cards. Output Tok/s, GPU %, CPU %, TTFT (with Prefill tok/s subtitle), Process Memory, Model Memory, Thermal State, GPU Frequency
  • 7 live charts. Tokens/sec, GPU utilization, CPU utilization, process memory, GPU/CPU/ANE/DRAM power, GPU frequency - all updating in real time
  • Power telemetry. Real-time GPU, CPU, ANE, and DRAM power consumption in watts via IOReport

Get started

brew install --cask uncsoft/anubis/anubis-oss

You need: macOS 15.0 (Sequoia) or later; Apple Silicon (M1 / M2 / M3 / M4 / M5 +) - Intel is not supported; 8 GB unified memory minimum (16 GB+ recommended for larger models)

Maintenance
Active
Last commit 2 months ago
Stars
218
+3 this week
Licence
GPL-3.0
Share-alike terms
Downloads for
None listed
No release files
Latest version
v3.9.0
Released 2 months ago
Built with
Swift
80% of the code

Is it looked after?

Contributors
1
Last 90 days
Issues
96% closed
1 still open
Pull requests
1 merged
0 waiting
Releases
21
21 in the last year

Similar repos

Repos similar to this one
RepoStarsLast commitLicenceDownloads for
jundot / omlx23,4754 days agoApache-2.0Mac
Neywa-Labs / nativ1,581todayMITMac
vllm-project / vllm-metal1,974todayApache-2.0Mac
More: languages, topics and project record

Languages

  • Swift 80%
  • HTML 16%
  • Shell 2%
  • PHP 1%

Topics

  • apple-silicon
  • benchmarking
  • gpu
  • inference
  • llm
  • local-llm
  • macos
  • mlx
  • native
  • ollama
  • performance
  • swiftui

Project record

  • JobLocal LLMs
  • StatusListed
  • Commits186
  • Forks17
  • Watching2
  • Stars in 28 days+8
  • CreatedFeb 7, 2026
  • First seen by usNov 7, 2026
  • CheckedNov 9, 2026

Type to search.

Try