Neural Compressor

Release: v3.10 (2026-09-29)Commit: de444feLicense: Apache-2.0

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

quantization and conversionv3.10releaseNeural CompressorPythonApache-2.0

FactsLicenseApache-2.0LanguagePythonKindquantization and conversionRelease2026-09-29PlatformsLinux, macOS, WindowsLinks to the projectpermissive

$ pip install neural-compressor-pt

Overview Install Use with Freeweights License Provenance

Overview

Intel's library for quantizing and pruning models across frameworks.

Kind: quantization and conversion
License: Apache-2.0
Language: Python
Platforms: Linux, macOS, Windows
Latest release: v3.10 (2026-09-29)
Repository: intel/neural-compressor

Topicsauto-tuningawqfp4gptqint4int8knowledge-distillationlarge-language-modelslow-precisionmxformatpost-training-quantizationpruning

Freeweights links to the project and does not host tool binaries.

Install

$ pip install neural-compressor-pt

$ pip install neural-compressor-pt

Checked against the project's README on 2026-11-15. The project's own instructions win when they differ: install docs

Freeweights links to the project and does not host tool binaries.

Use with Freeweights

Convert a catalog model

Download the weights from Freeweights first (HF_ENDPOINT or fw.py), then point the tool at the folder.

Catalog models it can run (3137)

135M-lc-100k-rope-12B a2-rl-e2egit_large-50-32B AesCode-32B AesCode-8B AFM-4.5B AFM-4.5B-Base AgentCPM-Report Agents-A1-4B AI21-Jamba-Reasoning-3B AI21-Jamba2-Mini AlchemistCoder-L-7B Alexandria-Gemma-4-12B-it-Ornith9-Summaries-LoRA-r128 Alexandria-Gemma-4-12B-it-Ornith9-Summaries-LoRA-r64 Alexandria-Gemma-4-12B-it-Qwen27-Knowledge-Units-LoRA-r128 Alexandria-Gemma-4-12B-it-Qwen27-Summaries-LoRA-r128 Alexandria-Gemma-4-12B-it-Qwen27-Summaries-LoRA-r64 Alexandria-Gemma-4-E4B-it-Qwen27-Knowledge-Units-LoRA-r128 ALLaM-7B-Instruct-preview AM-Thinking-v1 AMD-OLMo-1B AMD-OLMo-1B-SFT AMD-OLMo-1B-SFT-DPO Apertus-70B-2509 Apertus-70B-Instruct-2509 Apertus-8B-2509 Apertus-8B-Instruct-2509 Apertus-8B-Instruct-2509-unsloth-bnb-4bit Apertus-v1.1-0.5B Apertus-v1.1-0.5B-Instruct Apertus-v1.1-1.5B Apertus-v1.1-1.5B-Instruct Apertus-v1.1-4B Apertus-v1.1-4B-Instruct Apex-35B-V1.0 Apodex-1.1-mini Apriel-1.5-15b-Thinker Apriel-1.6-15b-Thinker Apriel-Nemotron-15b-Thinker Aquila-135M-Intermediate Aquila-VL-2B-Intermediate AquilaDense-16B AquilaMoE AquilaMoE-SFT Arcee-Maestro-7B-Preview Arete-27B AREX-2 AREX-2-6bit AREX-Base AREX-Turbo AstaBrief_8B AstaBrief_8B_SFT Aurora-Code-1 Baguettotron Baichuan-M2-32B BAR-2x7B-Base BAR-2x7B-Code BAR-2x7B-Code-SFT BAR-2x7B-Math BAR-2x7B-Math-SFT BAR-2x7B-Safety

and 3077 more.

License

License: Apache-2.0
Class: Permissive

Read the license

Freeweights links to the project and does not host tool binaries.

Provenance

From: intel <github.com/intel>Newsgroups: alt.freeweights.toolsSubject: Neural CompressorRelease: v3.10 (2026-09-29)Commit: de444feLicense: Apache-2.0

Repository: intel/neural-compressor
Pinned release: v3.10, 2026-09-29
Release commit: de444fef482c6b066d4f621780462b444e955f29
Default branch: main 9d95229f7e18c5e403b470934447134a7d611452
Fetched: 2026-11-15
Takedowns: None.

Freeweights links to the project and does not host tool binaries.

Get it

Install Project repository

Works with

3137 catalog models. See the list