Skip to content
shoehorn

Free alternatives to shoehorn

200 free apps like shoehorn, closest match first.

Top picks

  1. H

    huggingface-local-models

    Get

    huggingface-local-models is an agent skill for choosing and running language models locally with llama.cpp and GGUF files. It works on CPU, Apple Metal, NVIDIA CUDA and AMD ROCm. The skill searches the Hugging Face Hub for llama.cpp-compati

  2. H

    huggingface-best

    Get

    huggingface-best is an agent skill for finding the best model for a task. It reads what the user wants the model to do, such as coding, math and reasoning, chat, OCR, retrieval, speech recognition, image classification, multimodal work or a

  3. N

    nemo-mbridge-recipe-recommender

    Get

    Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal. Use

  4. Q

    qwencloud-model-selector

    Get

    An advisor skill from the QwenCloud project that recommends the right Qwen model and parameters. It works in two modes. In interactive advisory mode it asks diagnostic questions and recommends a model from the CDN catalogs. In cross-skill m

  5. F

    fine-tuning-expert

    Get

    fine-tuning-expert is an agent skill from the jeffallan claude-skills collection that helps a coding agent fine-tune large language models and adapt foundation models to specific tasks. It covers configuring parameter-efficient adapters suc

  6. Q

    qianwen-model-selector

    Get

    qianwen-model-selector is an agent skill from the QianWen-AI skills collection, listed on skills.sh. It helps an AI agent recommend the right Qwen model and its parameters for a task. It is triggered when someone is choosing between Qwen mo

More like shoehorn

7
T

tao-finetune-huggingface-model

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an

Get
8
B

BodhiApp

Run Open Source/Open Weight LLMs locally with OpenAI compatible APIs

Launch
9
A

Aikit

Fine-tune, build, and deploy open-source LLMs easily!

Launch
10
L

LocalAI

Unlock the power of AI with LocalAI, the ultimate AI model management tool

Launch
11
L

llmfit-hardware-model-matcher

Terminal tool that detects your hardware and recommends

Get
12
H

huggingface-community-evals

Run evaluations for Hugging Face Hub models

Get
13
Q

quantized-export

Export a promoted fine-tuned model in the right deployment format

Get
14
T

TurboLLM

Run any local LLM engine, auto-tuned to your GPU

Launch
15
W

whatcani.run

Find the best models and how to run them locally

Launch
16
N

nemo-mbridge-perf-activation-recompute

Validate and use selective and full activation recompute in Megatron Bridge

Get
17
I

import-model

Importing a new model architecture into MAX from a Hugging Face model ID

Get
18
H

HyperQwen

Serve large Qwen models fast on the GPUs you actually own

Launch
19
J

jetson-inference-mem-tune

Pick the serving stack and per-runtime memory flags

Get
20
T

tao-port-huggingface-model

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit

Get
21
H

huggingface/hugging-face-model-trainer

Train models with TRL: SFT, DPO, GRPO, GGUF conversion

Get
22
W

WebLLM Chat

Chat with AI large language models running natively in your browser

Launch
23
H

huggingface-llm-trainer

Train or fine-tune language and vision models using TRL

Get
24
T

transformers

Hugging Face Transformers for loading Hub models, running pipeline inference

Get
25
Q

Quail

Local model server for GGUF and MLX models on Apple silicon

Launch
26
N

nemo-mbridge-perf-moe-dispatcher-selection

Choose the right MoE token dispatcher

Get
27
X

Xybrid

Cross-platform on-device AI toolkit

Launch
28
C

Convert to ONNX

Convert a Hugging Face model to ONNX format

Launch
29
T

TRAE-Ollama-Bridge

Encapsulate the local Ollama into an OpenAI-compatible API

Launch
30
M

Minion

A tiny single-file coding agent for self-hosted models

Launch
31
M

Matrixhub

An Open-source, self-hosted AI model hub

Launch
32
L

Llmaker

Selfhost modern LLM stacks. Run the whole fleet from your terminal

Launch
33
H

huggingface/hf-cli

HF CLI tool for Hub operations

Get
34
N

nemo-automodel-model-onboarding

Guide for onboarding new model architectures into NeMo AutoModel

Get
35
O

OfflineLLM

Private on-device AI chat for Android

Launch
36
F

Frugon

Free, local, open-source LLM cost analyzer

Launch
37
N

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters

Get
38
L

Litmux

Unit tests for AI. Test prompts, compare models, save money

Launch
39
L

Llamafarm

Deploy any AI model, agent, database, RAG

Launch
40
B

build-models

Package and build custom AI models with Cog for deployment on Replicate

Get
41
N

nanochat-llm-training

Train your own GPT-2 level LLM for under $100

Get
42
M

Msty

Use Llama 3, GPT-4o, Mixtral, Gemma, etc. on your computer. Ultimate privacy

Launch
43
L

LMRing

Open-source, self-hostable LLM arena

Launch
44
C

Chipper

AI interface for tinkerers (Ollama, Haystack RAG, Python)

Launch
45
N

nemo-automodel-recipe-development

Create and modify NeMo AutoModel training and evaluation recipes

Get
46
Q

Qwen38 Uncensored

Local Qwen 3.8 27B uncensored Q4_K_M + harvested SYSTEM pack

Launch
47
H

huggingface-tool-builder

Build tool/scripts or achieve a task where

Get
48
N

NadirClaw

Source-available LLM router and AI cost optimizer

Launch
49
C

compare-models

Compare Replicate models by cost, speed, quality, and capabilities

Get
50
J

jetson-llm-benchmark

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp

Get

About shoehorn

S

shoehorn

Make any language model fit your machine

shoehorn is a tool for making a language model fit the memory your machine actually has. Preset quantizations ignore your hardware: you pick one that fits and either waste quality headroom or find out at load time that it does not fit. shoehorn starts from the memory you have, subtracts what inference needs, and solves a per-tensor mixed-precision assignment, so it spends the remaining budget on the tensors where extra precision buys the most quality. The site's example fits a Qwen3 4B model into a 519 MiB weights budget, using 99.998 percent of it. The workflow quantizes a BF16 GGUF file with an importance matrix, then runs the result with llama.cpp, which must be on your PATH. The command line tool includes a local web app, started with shoehorn ui, where you pick a model, press one button and chat. The site also has a Find models page that scans popular Hugging Face models for ones that fit a chosen machine, such as a Mac with 8 to 128 GB or a GPU with 8 to 32 GB of VRAM, and a context length setting. Installation is available through Homebrew, as release downloads for macOS, Linux and Windows, or from source with cargo. The tool is MIT licensed. Its quantizer is written from scratch in Rust, and it produces standard GGUF v3 files that llama.cpp based tools can load.

Price
Open source
Category
Finance
Website
notactuallytreyanastasio.github.io