Skip to content

QuantLLM is a Python library designed for developers, researchers, and teams who want to fine-tune and deploy large language models (LLMs) efficiently using 4-bit and 8-bit quantization techniques.

active 2025-04-262026-04-29 (UTC)

Partial coverage12,343 / 14,052 hourly files (88%) · 2 absent upstream · 1,703 failed, retryable2025-01-022026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
119
Pushes
72
Pull requests
14
Issues
6
Stars
7
Forks
1

Activity over time

Daily event counts in the loaded window

Line chart, 369 days from 2025-04-26 to 2026-04-29. Pushes: 72 total, peak 10 in a day. Pull requests: 14 total, peak 6 in a day. Issues: 6 total, peak 2 in a day. Comments: 8 total, peak 5 in a day. Stars: 7 total, peak 3 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
codewithdark-git9672142
Copilot9405
algora-pbc[bot]1001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#27codewithdark-git2026-04-25 08:20
    Add architecture registration + fallback loading path for newly released HF model types
  • Issue#26codewithdark-git2026-04-25 07:11
    New LLM Architectures Not Recognized by Transformers — Add Flexible Model Class Registration and Fallback System
  • Issue#26codewithdark-git2026-04-25 07:11
    New LLM Architectures Not Recognized by Transformers — Add Flexible Model Class Registration and Fallback System
  • Issue comment#25Copilot2026-04-25 06:30
    Centralize Turbo export/push config, make quantization defaults deterministic, and prepare v2.1 pre-release
  • Issue#24codewithdark-git2026-04-24 20:14
    Centralize config for export/push parameters and improve quantization default handling
  • Issue#24codewithdark-git2026-04-24 20:14
    Centralize config for export/push parameters and improve quantization default handling
  • Releasecodewithdark-git2025-12-21 15:04
    QuantLLM v2.0
  • Issue comment#5codewithdark-git2025-07-27 13:26
    [BUG] Brief description of the bug in QuantLLM
  • Issue comment#5algora-pbc[bot]2025-07-27 13:25
    [BUG] Brief description of the bug in QuantLLM
  • Issue#16codewithdark-git2025-06-03 20:03
    Error in QuantLLM.save_quantized_model when saving quantized model
  • Pull request#15codewithdark-git2025-05-28 00:07
  • Pull request#14codewithdark-git2025-05-27 23:01
  • Pull request#13codewithdark-git2025-05-27 22:23
  • Pull request#13codewithdark-git2025-05-27 22:22
  • Pull request#11codewithdark-git2025-05-27 20:36
  • Pull request#10codewithdark-git2025-05-26 06:49
  • Pull request#9codewithdark-git2025-05-26 06:15
  • Pull request#9codewithdark-git2025-05-26 06:13
  • Pull request#8codewithdark-git2025-05-25 09:01
  • Pull request#8codewithdark-git2025-05-25 09:01
  • Pull request#7codewithdark-git2025-05-25 08:31
  • Pull request#7codewithdark-git2025-05-25 08:30
  • Pull request#6codewithdark-git2025-05-25 07:49
  • Pull request#6codewithdark-git2025-05-25 07:49
  • Issue#2codewithdark-git2025-04-27 14:05
    Error Occur when Calculate the gradients

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 7 stars here means stars gained during the window, not the repo's star count.