Skip to content

⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.

Swift · active 2026-03-302026-08-08 (UTC)

Partial coverage11,862 / 13,269 hourly files (89%) · 2 absent upstream · 1,403 failed, retryable2025-02-042026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
422
Pushes
169
Pull requests
30
Issues
8
Stars
99
Forks
9

Activity over time

Daily event counts in the loaded window

Line chart, 132 days from 2026-03-30 to 2026-08-08. Pushes: 169 total, peak 18 in a day. Pull requests: 30 total, peak 9 in a day. Issues: 8 total, peak 2 in a day. Comments: 31 total, peak 8 in a day. Stars: 99 total, peak 15 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
solderzzc205169226
Copilot310017
ericjlake10044
luiz2907882011
roydsouza2020
rednaxela59502002
0xClandestine1010
notatestuser1001
4external1000

Recent activity

Latest issues, pull requests and releases

  • Pull request#125solderzzc2026-08-07 22:07
  • Pull request#125solderzzc2026-08-07 18:23
  • Pull request#105solderzzc2026-05-13 05:55
  • Issue#72solderzzc2026-05-08 19:41
    Streams experts not working with draft model?
  • Pull request#104roydsouza2026-05-08 04:07
  • Pull request#104roydsouza2026-05-07 23:34
  • Issue#974external2026-04-30 05:44
    SwiftBuddy Chat: [Error: The operation couldn’t be completed. (Jinja.TemplateException error 1.)]
  • Pull request#95solderzzc2026-04-28 06:27
  • Issue#87solderzzc2026-04-27 20:05
    EXC_BREAKPOINT (SIGTRAP)
  • Issue#87solderzzc2026-04-27 06:29
    EXC_BREAKPOINT (SIGTRAP)
  • Pull request#90ericjlake2026-04-27 05:11
  • Pull request#88ericjlake2026-04-26 18:39
  • Issue comment#84ericjlake2026-04-26 07:40
    Qwen3-A3B full-RAM generation: 18 → 63 tok/s on M1 Ultra 64GB after `needsMoeFlush` gate + prompt-cache bleed fixes
  • Pull request#86solderzzc2026-04-26 06:43
  • Issue comment#84ericjlake2026-04-26 04:18
    Qwen3-A3B full-RAM generation: 18 → 63 tok/s on M1 Ultra 64GB after `needsMoeFlush` gate + prompt-cache bleed fixes
  • Pull request#85ericjlake2026-04-26 04:17
  • Issue#84ericjlake2026-04-26 01:28
    Qwen3-A3B full-RAM generation: 18 → 63 tok/s on M1 Ultra 64GB after `needsMoeFlush` gate + prompt-cache bleed fixes
  • Pull request#780xClandestine2026-04-24 22:23
  • Releasegithub-actions[bot]2026-04-23 20:31
    SwiftLM b554
  • Pull request#76solderzzc2026-04-23 07:10
  • Releasegithub-actions[bot]2026-04-23 03:49
    SwiftLM b537
  • Issue#71solderzzc2026-04-22 18:17
    [Bug]: MLXLLM Gemma 4 attention crashes when kvBits is set
  • Pull request#57solderzzc2026-04-17 04:22
  • Issue comment#60notatestuser2026-04-17 04:22
    fix: resolve Gemma4 K-eq-V broadcast crash (closes #59)
  • Pull request#60solderzzc2026-04-16 23:21

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 99 stars here means stars gained during the window, not the repo's star count.