alt.freeweights.tools / ik_llama.cpp

From: ikawrakow <github.com/ikawrakow>Newsgroups: alt.freeweights.toolsSubject:

ik_llama.cpp

Release: noneCommit: fcf7b36License: MIT

llama.cpp fork with extra quantization types and faster CPU and hybrid inference.

inference engineno releasereleaseik_llama.cppC++MIT

FactsLicenseMITLanguageC++Kindinference engineReleasenonePlatformsLinux, macOS, WindowsLinks to the projectpermissive

$ git clone https://github.com/ikawrakow/ik_llama.cpp

Overview Install Use with Freeweights License Provenance

Overview

llama.cpp fork with extra quantization types and faster CPU and hybrid inference.

Kind: inference engine
License: MIT
Language: C++
Platforms: Linux, macOS, Windows
Latest release: no release
Repository: ikawrakow/ik_llama.cpp

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

Install

$ git clone https://github.com/ikawrakow/ik_llama.cpp

$ git clone https://github.com/ikawrakow/ik_llama.cpp

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

Run 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 (1944)

abacusai_Smaug-Humanizer-GGUF Accio-Lab_occamy-1.0-GGUF AesCode-32B-GGUF AesCode-8B-GGUF AgentCPM-Explore-GGUF AgentCPM-Report-GGUF agentica-org_DeepCoder-14B-Preview-GGUF agentica-org_DeepScaleR-1.5B-Preview-GGUF agentica-org_DeepSWE-Preview-GGUF ai21labs_AI21-Jamba-Reasoning-3B-GGUF ai21labs_AI21-Jamba2-Mini-GGUF ai9stars_G9v3-3B-GGUF alamios_Mistral-Small-3.1-DRAFT-0.5B-GGUF AlchemistCoder-L-7B-GGUF Alibaba-NLP_Tongyi-DeepResearch-30B-A3B-GGUF allenai_Olmo-3-7B-Instruct-GGUF allenai_Olmo-3-7B-Think-GGUF allenai_Olmo-3.1-32B-Instruct-GGUF allenai_Olmo-3.1-32B-Think-GGUF allenai_olmOCR-2-7B-1025-GGUF allenai_olmOCR-7B-0225-preview-GGUF AM-Thinking-v1-GGUF AMD-OLMo-1B-SFT-DPO-GGUF AMD-OLMo-1B-SFT-GGUF Apertus-70B-Instruct-2509-GGUF Apertus-8B-Instruct-2509-GGUF Apexintelligence-AI_Apex-35B-V1.0-GGUF apodex_Apodex-1.1-mini-GGUF Apriel-1.5-15b-Thinker-GGUF Apriel-Nemotron-15b-Thinker-GGUF arcee-ai_AFM-4.5B-GGUF arcee-ai_Arcee-Maestro-7B-Preview-GGUF arcee-ai_GLM-4-32B-Base-32K-GGUF ATH-MaaS_OvisOCR2-GGUF AutoGLM-Phone-9B-GGUF BAAI_AREX-2-GGUF BAAI_AREX-Base-GGUF BAAI_AREX-Turbo-GGUF baichuan-inc_Baichuan-M2-32B-GGUF baidu_ERNIE-4.5-21B-A3B-PT-GGUF baidu_ERNIE-4.5-21B-A3B-Thinking-GGUF Beam-1.0-501B-A23B-GGUF Beam-1.0-501B-A23B-GGUF bert-base-uncased bge-small-en-v1.5-GGUF Biggie-SmoLlm-0.4B BitCPM-CANN-0.5B-gguf BitCPM-CANN-1B-gguf BitCPM-CANN-3B-gguf BitCPM-CANN-8B-gguf BitCPM4-0.5B-GGUF BitCPM4-1B-GGUF bitnet-b1.58-2B-4T-gguf bitnet-embedding-0.6b bitnet-embedding-270m Bonsai-27B-GGUF Bunny-Llama-3-8B-V-gguf Bunny-v1_0-4B-gguf ByteDance-Seed_Seed-OSS-36B-Instruct-GGUF bytkim_Qwen3.8-27B-pi-GGUF

and 1884 more.

License

License: MIT
Class: Permissive

Read the license

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

Provenance

From: ikawrakow <github.com/ikawrakow>Newsgroups: alt.freeweights.toolsSubject: ik_llama.cppRelease: noneCommit: fcf7b36License: MIT

Repository: ikawrakow/ik_llama.cpp
Pinned release: none
Release commit: not known
Default branch: main fcf7b364786ec621d0c53eae39223efc5492b8c5
Fetched: 2026-11-15
Takedowns: None.

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

Get it

Install Project repository

Works with

1944 catalog models. See the list