Skip to content
PrismML

Free alternatives to PrismML

200 free apps like PrismML, closest match first.

Top picks

  1. X

    Xybrid

    Launch

    Run ML models on-device or in the cloud with intelligent routing. Zero infrastructure. Privacy-first, cost-optimized. Any model. Any platform.

    FreeOpen source

  2. P

    Prismos AI

    Launch

    Local-first desktop AI: chat with your files, turn one line into a living 3D scene, investigate logs and harden configs. Runs on your laptop, works offline.

    FreeOpen source

  3. W

    whatcani.run

    Launch

    whatcani.run helps you find the best AI models to run locally and how to run them, based on real data from trials that people ran on their own hardware. Each model is listed with its runtime, decode and prefill speed, time to first token, p

    FreeOpen source

  4. A

    Artifex

    Launch

    We develop task-specific Small Language Models for any text processing task and language. Replace calls to LLM APIs with your own SmallLMs to cut costs by up to 90%, get enhanced data privacy, higher performance and lower latency.

    FreeOpen source

  5. B

    Benchmark Heaven

    Launch

    Benchmark Heaven compares AI models on cost and capability, with benchmark results, charts and provider prices. It is the home of JevBench, a decision-model benchmark that measures accuracy, calibration, latency and cost. The site has a cos

    Free

  6. L

    LocalAI

    Launch

    Local AI Playground, known as local.ai, is a free and open source desktop app for experimenting with AI models on your own computer, offline and in private. The app manages models, verifies their digests and runs an inference server, so you

    FreeOpen source

More like PrismML

7
H

huggingface-best

About finding the best, top, or recommended model for a task

Get
8
M

Memlayer

Plug-and-play memory for LLMs in 3 lines of code

Launch
9
U

Uncensored-Local-AI-Multiplatform

A cross-platform Flutter app that runs uncensored, 100% offline open-source…

Launch
10
S

Slotstream

Run a 105 GB AI model on a Mac that can't hold it

Launch
11
L

Llamafarm

Deploy any AI model, agent, database, RAG

Launch
12
N

Nativ

Local AI, native to your Mac

Launch
13
O

OfflineLLM

Private on-device AI chat for Android

Launch
14
V

VerifyFetch

Your users download a 4GB AI model, the connection drops at 3.8GB

Launch
15
A

AgentOp

Run a real LLM in your browser. No install, no server

Launch
16
A

AI LLM Comparison

A website where you can compare every AI Model

Launch
17
O

OpenRouter Model Price Comparison

Compare pricing across different AI models available on OpenRouter

Launch
18
R

Reins

Local AI chat for iPhone, iPad and Mac

Launch
19
P

Picollm

On-device LLM Inference Powered by X-Bit Quantization

Launch
20
P

Prism

Prism is a premium AI news digest built for people who value clarity over noise

Launch
21
P

Prismor

Self-hosted runtime control plane for AI agents

Launch
22
T

Transformerlab App

The open source research environment for AI researchers to seamlessly train

Launch
23
L

Litmux

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

Launch
24
L

LMRing

Open-source, self-hostable LLM arena

Launch
25
A

AIModels.fyi

Find the AI breakthroughs that actually matter

Launch
26
N

Nesa

Run AI models end-to-end encrypted

Launch
27
M

Matrixhub

An Open-source, self-hosted AI model hub

Launch
28
C

Coreai Model Zoo

Downloadable models and conversion recipes for Apple's Core AI on iPhone and Mac

Launch
29
J

Janas

37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs…

Launch
30
W

Web LLM

High-performance In-browser LLM Inference Engine

Launch
31
C

ChatLLM-Web

Private local model studio, AI chat

Launch
32
M

mlx-serve

Native LLM inference server for Apple Silicon

Launch
33
T

TheWhisper

Optimized Whisper models for streaming and on-device use

Launch
34
P

PixelVerse t1

An advanced logical thinking and reasoning AI model

Launch
35
Q

Quail

Local model server for GGUF and MLX models on Apple silicon

Launch
36
V

vllm-mlx

High-performance OpenAI and Anthropic compatible LLM inference server

Launch
37
M

MLX Tune

Fine-tune LLMs on your Mac with Apple Silicon

Launch
38
B

BodhiApp

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

Launch
39
L

llama.ui

A minimal interface for AI Companion that runs entirely in your browser

Launch
40
N

NadirClaw

Source-available LLM router and AI cost optimizer

Launch
41
T

ToolNeuron

Encrypted & Privacy First, On Android Device AI App

Launch
42
P

pooled

Peer-to-peer LLM inference in the browser: pool your devices

Launch
43
N

Netron

Visualizer for neural network and machine learning models

Launch
44
E

Efficient-LLMs-Survey

[TMLR 2024] Efficient Large Language Models: A Survey

Launch
45
M

Memvid

Memory layer for AI Agents

Launch
46
L

Ling

The LLMs' framework optimized for ultra-fast response times

Launch
47
T

TurboLLM

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

Launch
48
A

AI//COST

Independent directory that tracks source-verified API pricing

Launch
49
S

Sipp

AI inference, packed simply

Launch
50
G

Graviton

500B+ LLMs on a Mac Mini

Launch

About PrismML

P

PrismML

Concentrating intelligence

PrismML builds small, efficient AI models: 1-bit and ternary models called Bonsai, which the company says pack advanced reasoning, tool use and multimodal abilities into phones, laptops, wearables and efficient data centres. Its Bonsai 2 family spans 2 billion to 27 billion parameters, with memory footprints from about 0.43 GB to 5.9 GB. The company says the family uses far less memory and energy than standard models, and it publishes benchmark comparisons for intelligence density, throughput in tokens per second and energy per token across hardware platforms. The models are available to download, and there is a demo to try. The Bonsai Image model is also listed, along with a 16-bit standard version for comparison. The company points to a whitepaper for its evaluation method. PrismML is focused on AI research into efficiency, and it has a careers page for people who want to join the team.

Category
AI
Website
prismml.com