Skip to content

[EMNLP Findings 2024] MobileQuant: Mobile-friendly Quantization for On-device Language Models

active 2024-08-182025-09-28 (UTC)

Complete coverage26,550 / 26,550 hourly files (100%) · 2 absent upstream2023-08-152026-08-25 (UTC)
Events
141
Pushes
11
Pull requests
0
Issues
21
Stars
66
Forks
6

Activity over time

Daily event counts in the loaded window

Line chart, 407 days from 2024-08-18 to 2025-09-28. Pushes: 11 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 21 total, peak 3 in a day. Comments: 33 total, peak 6 in a day. Stars: 66 total, peak 8 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
fwtan3611022
CHNtentes5003
taeyeonlee4002
BlindDeveloper3001
npu-mi-ji3000
mhs4670go3001
zhuipiaochen3001
The-Coder-Kishor2001
chenjun2hao2001
jds2501000
Abhishek83941001
shifeiwen1000
tom-pollak1000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#14mhs4670go2025-04-20 23:18
    Running the model with gen2 device
  • Issue#14mhs4670go2025-04-20 23:18
    Running the model with gen2 device
  • Issue comment#14fwtan2025-04-18 21:23
    Running the model with gen2 device
  • Issue#14mhs4670go2025-04-11 09:18
    Running the model with gen2 device
  • Issue comment#13fwtan2025-02-21 04:26
    What is full W8A8?
  • Issue#13jds2502025-02-13 07:50
    What is full W8A8?
  • Issue comment#12chenjun2hao2025-01-08 06:03
    will it work well on 8gen1
  • Issue comment#12fwtan2025-01-06 14:49
    will it work well on 8gen1
  • Issue#12chenjun2hao2025-01-06 02:17
    will it work well on 8gen1
  • Issue comment#11The-Coder-Kishor2025-01-03 13:33
    Issue with .bin generation
  • Issue comment#11fwtan2025-01-03 12:57
    Issue with .bin generation
  • Issue#11The-Coder-Kishor2024-12-30 02:22
    Issue with .bin generation
  • Issue comment#10zhuipiaochen2024-12-17 08:34
    Does this project support Qualcomm's 8gen2
  • Issue#10zhuipiaochen2024-12-17 08:34
    Does this project support Qualcomm's 8gen2
  • Issue#10zhuipiaochen2024-12-17 08:14
    Does this project support Qualcomm's 8gen2
  • Issue comment#9fwtan2024-11-16 19:03
    There is an error when using model.generation
  • Issue#9npu-mi-ji2024-11-11 12:26
    There is an error when using model.generation
  • Issue#8npu-mi-ji2024-11-11 05:13
    Would there be any issues if the ElementwiseAdd operation is not quantized?
  • Issue comment#7CHNtentes2024-11-04 09:28
    vram usage
  • Issue comment#8fwtan2024-11-03 11:13
    Would there be any issues if the ElementwiseAdd operation is not quantized?
  • Issue comment#7fwtan2024-11-03 10:55
    vram usage
  • Issue#8npu-mi-ji2024-10-30 03:45
    Is there a problem with not quantizing the ElementwiseAdd operation?
  • Issue#7CHNtentes2024-10-29 03:50
    vram usage
  • Issue comment#6fwtan2024-10-14 12:21
    How to generate config.json for HFForCausalLM?
  • Issue comment#6CHNtentes2024-10-14 12:11
    How to generate config.json for HFForCausalLM?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 66 stars here means stars gained during the window, not the repo's star count.