Comparison

Liquid Apollo vs MLX Benchmarks

Price, ratings, monetisation and update history for both apps, side by side — with what reviewers say about each.

Head to head
About

Liquid Apollo

Access a wide range of AI language models, from local on-device options to those available through external APIs. This app allows you to connect to open-source and privately hosted LLMs, offering a customizable client for diverse AI interactions.

Highlights
  • Local AI model support
  • OpenRouter API integration
  • Custom backend LLM connection
  • Private on-device LLM execution
  • Access to diverse open-source models
  • Connect to privately hosted LLMs
Features
Read full description

Chat with private, local AI models, connect to every open source AI, or your own locally-hosted private LLMs. Apollo is your own customizable client for accessing language models from all around the web. Local model support (powered by LEAP, a Liquid AI product): run smaller LLMs privately and securely on-device. OpenRouter support: bring an OpenRouter API key to chat with every model on the web. Just sign in by creating an account over at OpenRouter and paste it in to Apollo to access nearly every model, from open source models like Meta Llama 3, to closed source models like OpenAI’s ChatGPT-4. Custom Backend support: want ChatGPT at home? Run an LLM on your computer with tools like LM Studio or Ollama and connect to it with Apollo to host your own private ChatGPT-like mobile app for your family.

About

MLX Benchmarks

Features
Read full description

MLX Benchmark measures how fast large language models run on your iPhone and iPad, entirely on device, with Apple's open-source MLX framework. STANDARD BENCHMARK Every device runs the same test: a fixed 512-token prompt, then exactly 128 tokens generated with greedy decoding. One warm-up run and three measured runs, with medians reported. Because the input and settings never change, your results are directly comparable with any other device. COMMUNITY Share your standard runs anonymously and compare your device with everyone else's: • Device ranking: median generation speed, prefill speed or time to first token for each model • Models on a device: how speed changes with model size, next to the memory-bandwidth estimate for that device • Comparison: your run next to the community medians of other devices DETAILED MEASUREMENTS • Generation and prefill speed, in tokens per second • Time to first token, tokenization and model load time • Per-token latency as a timeline and a distribution, with P50, P95, P99 and jitter • Memory: model weights, KV cache and activations, and the peak against the memory iOS lets the app use • Thermal state and Low Power Mode, so throttled runs are easy to spot MODELS Browse a catalog of open models supported by MLX, such as Qwen and Llama in 4-bit. Each model is downloaded on its first run; see what is stored on your device and delete what you no longer need. CUSTOM RUNS Try your own prompt, generation length and number of iterations. Custom results stay on your device. PRIVACY No account and no tracking. Only standard runs are shared, and only while sharing is on: device model and hardware (core counts, memory), the model tested, app and OS version, and the measured metrics. Nothing that identifies you.

Screenshots

Liquid Apollo4 screens
MLX Benchmarks4 screens

Verdict

The call

The clearest difference is update cadence: Liquid Apollo at every 8 days against MLX Benchmarks's every 6 months. On price, ads, in-app purchases and device support there is nothing between them.

Scored on Price · Rating · Positive reviews · Number of ratings · Update frequency · Ads · In-app purchases · Monetization · Best chart rank · Devices · Requires iOS

CostPrice · In-app purchases · Ads · Monetization

Both are free to download. Neither carries in-app purchases, so what you see is what you pay.

UpkeepUpdate frequency

Liquid Apollo ships an update every 8 days, MLX Benchmarks every 6 months. Both last shipped on November 18, 2026.

Scorecard1 real difference · 9 level
Liquid Apollo versus MLX Benchmarks: the parameters behind the verdict, then further details
ParameterLiquid ApolloMLX Benchmarks
PriceFreeFree
Rating4.5 (681 ratings) — better—
Positive reviews67.8% of reviews—
Number of ratings681 — better—
Update frequencyEvery 8 days — betterEvery 6 months
AdsNoNo
In-app purchasesNoNo
MonetizationFree—
DevicesiPhone, iPad, Mac — betteriPhone, iPad
Requires iOS18.0 — better18.6
Further details — not scored
Size158 MB24 MB
Age rating12+4+
DeveloperLiquid AI, Inc.Costantino Pistagna

Bugs and requests

Liquid Apollo

Reported bugs

6 issues
  • Unable to download Liquid Models
  • Deleted locally installed models
  • OpenRouter support crashes the app
  • Voice list doesn't load all available voices
  • Backspace lag leading to unintended text deletion
Show 1 more
  • Inconsistent behavior when using code blocks

Requested features

10 requests
  • Add support for more open-source models (e.g. Gemma 3)
  • Implement image generation and upload functionality
  • Allow scheduling of asynchronous tasks
  • Integrate with Hugging Face model repository
  • Provide built-in prompt library
Show 5 more
  • Add MCP (Multimodal Conversation Protocol) support
  • Enable direct OpenAI API integration
  • Improve voice chat functionality
  • Add option to delete all chat history
  • Implement search and filtering for chat history

MLX Benchmarks

Not enough reviews yet to summarise bugs or requests.

In-app purchases

None

Liquid Apollo

No in-app purchases

None

MLX Benchmarks

No in-app purchases

Questions

Is Liquid Apollo free?
Liquid Apollo is free to download, with no in-app purchases.
Is MLX Benchmarks free?
MLX Benchmarks is free to download, with no in-app purchases.
Do Liquid Apollo or MLX Benchmarks have ads?
Neither Liquid Apollo nor MLX Benchmarks shows ads.
Which is updated more often, Liquid Apollo or MLX Benchmarks?
Liquid Apollo ships an update every 8 days, and MLX Benchmarks every 6 months. Most recently, Liquid Apollo was updated on November 18, 2026 and MLX Benchmarks on November 18, 2026.

Other comparisons