Skip to content

repository to draft PRs to official mlx-examples

active 2025-03-272026-06-23 (UTC)

Partial coverage11,274 / 12,018 hourly files (94%) · 2 absent upstream · 742 failed, retryable2025-03-282026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
796
Pushes
8
Pull requests
16
Issues
14
Stars
610
Forks
81

Activity over time

Daily event counts in the loaded window

Line chart, 454 days from 2025-03-27 to 2026-06-23. Pushes: 8 total, peak 2 in a day. Pull requests: 16 total, peak 2 in a day. Issues: 14 total, peak 2 in a day. Comments: 56 total, peak 8 in a day. Stars: 610 total, peak 11 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

Recent activity

Latest issues, pull requests and releases

  • Issue#1418uogbuji2026-04-24 05:08
    [whisper] `KeyError: 'words'` on transcription (with `--task translate`)
  • Issue comment#1254AngeloSavich2026-04-04 09:29
    mlx_whisper memory usage keeps growing for every new audio chunk processed with word_timestamps on.
  • Issue#1412ilyasmukiev2026-03-26 12:24
    [whisper] Add Flash Attention and batched decoding for up to 10x speedup
  • Issue comment#1408deardaveed2026-03-09 08:17
    mlx_lm: TokenizerWrapper drops 'eos_token_ids' array, breaking conversational stop tokens
  • Issue#1405Vlor9992026-02-12 10:35
    [Model Request] Porting Nvidia PersonaPlex-7B (Moshi architecture) & Mimi Codec
  • Pull request#1403stefpi2026-01-10 23:24
  • Pull request#1400DePasqualeOrg2025-12-15 09:19
  • Pull request#1399DePasqualeOrg2025-12-14 17:56
  • Issue#1397awni2025-12-03 18:30
    N
  • Issue#1397eduard95032025-12-03 18:25
    N
  • Pull request#1393seyeong-han2025-11-17 21:36
  • Issue#1391FredrikKarlssonSpeech2025-11-06 07:18
    Using fine tuned whisper models in MLX must support beam search
  • Pull request#1390angeloskath2025-10-07 18:19
  • Issue comment#1379SSusantAchary2025-10-05 12:49
    Support for Qwen-Image generation
  • Issue comment#1170mattharrison2025-09-20 16:16
    mlx_lm.server: how to set context size?
  • Pull request#1388awni2025-09-03 20:18
  • Pull request#1388awni2025-09-03 20:18
  • Issue comment#1379zyfewq2025-08-30 23:51
    Support for Qwen-Image generation
  • Issue#1372awni2025-08-29 14:53
    Error in WWDC25 sample: `Explore_language_models_on_Apple_silicon_with_MLX.ipynb`
  • Issue comment#155KatoStevenMubiru2025-08-26 07:22
    Contribute Hugging Face models to the MLX Community
  • Issue comment#155awni2025-08-25 16:47
    Contribute Hugging Face models to the MLX Community
  • Pull request#1386awni2025-08-25 16:44
  • Issue#1384zyfy292025-08-23 11:38
    can't specify temperature for whisper model
  • Pull request#1383vincentamato2025-08-16 04:10
  • Issue#1382kudla2025-08-14 17:09
    How to fine tune quantized modeling convert it to GGUF still been quantized?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 610 stars here means stars gained during the window, not the repo's star count.