Skip to main content

cutter/quantizor for gguf

install it via pip/pip3

pip install gguf-cutter

download the cutter by (if no py command; use python/python3 instead)

py -m gguf_cutter

how to use it

tag: q2_k, q3_k_s, q3_k_m, q3_k_l, q4_k_s, q4_k_m, q5_k_s, q5_k_m, q6_k, q5_0, q5_1, q4_0, q4_1, q8_0

.\quantizor.exe [input_path] [output_path] [tag]

example:

if you want to cut a f16 gguf into q4_k_m, you should execute the command above in that way (put your f16 gguf file in the current directory with quantizor.exe together)

.\quantizor.exe your-gguf-f16.gguf output-gguf-q4_k_m.gguf q4_k_m

then, after completing the process, the quantized q_4_k_m will be saved in the current directory

Metadata

Release files for gguf-cutter 0.0.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for gguf-cutter 0.0.4
File Size Uploaded
gguf_cutter-0.0.4.tar.gz 2.6 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for gguf-cutter 0.0.4
File Interpreter ABI Platform
gguf_cutter-0.0.4-py2.py3-none-any.whl Python 2, Python 3 none any Details

Total release size: 5.9 kB

Release files / gguf_cutter-0.0.4.tar.gz

Download URL gguf_cutter-0.0.4.tar.gz
Size 2.6 kB
Tags Source
SHA-256 checksum
How to use checksums
98caaf7f39986430b17c8d89c1d6c130b4ae1f205cacc4ffa6090e7acedb0f38
BLAKE2b-256 checksum
How to use checksums
c7a5f47e5f4e60fd1a9ad661e5b3f3be17f373eb887f9952afab1e21cd60aa8c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.11.4

Release files / gguf_cutter-0.0.4-py2.py3-none-any.whl

Download URL gguf_cutter-0.0.4-py2.py3-none-any.whl
Size 3.3 kB
Tags Python 2 Python 3
SHA-256 checksum
How to use checksums
d7c82b1594e00b4a21096e1b69a7c83abbdd512be7c59f42ae873cca9b9c6558
BLAKE2b-256 checksum
How to use checksums
04e6ccff281b31b279e69460a3dd5f5ae30ed528a51e267a7f03101df347d029
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.11.4

Release history Release notifications | RSS feed

This release

0.0.4 This release

2 release files

0.0.3

2 release files

0.0.2

2 release files

0.0.1

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page