SparkDeck vs LM Pocket
Price, ratings, monetisation and update history for both apps, side by side — with what reviewers say about each.
SparkDeck
Read full descriptionHide full description
SparkDeck puts your NVIDIA DGX Spark in your pocket. See the GPU and memory live, chat with the models running on your desk, open a terminal and control your containers, all from your iPhone. YOUR SPARK AT A GLANCE • GPU load with a live trace, unified memory, temperature, power and storage. • The containers that are running, right on the dashboard. • A reading your Spark can't give shows a dash, never a made-up number. CHAT WITH YOUR OWN MODELS • Talk to the models your Spark serves with Ollama, vLLM or another OpenAI-compatible server. • Your conversations go between your iPhone and your Spark, not through a cloud service. • Get a notification when a reply finishes while SparkDeck is in the background. A REAL TERMINAL (PRO) • A full SSH terminal with several sessions, plus keys for esc, ctrl, tab and the arrows. • Sign in with your password or an Ed25519 key. Your password stays in this iPhone's Keychain. CONTAINERS (PRO) • Start, stop and restart Docker containers, and see why one failed. EASY SETUP SparkDeck finds your Spark on your Wi-Fi. Sign in with the account you use on your Spark, and SparkDeck installs its small agent (sparkdeck-agent, published on PyPI) for live stats, chat and Docker. Away from home, connect over Tailscale. FREE AND PRO SparkDeck is free with live stats, 25 chat messages a day and one device. Pro, a monthly or annual subscription, adds the terminal, Docker controls, unlimited chat and more devices. Subscriptions renew automatically unless cancelled at least 24 hours before the end of the period; manage them in your App Store account settings. REQUIREMENTS iOS 18 or later, and an NVIDIA DGX Spark or another GB10 system, such as the ASUS Ascent GX10, on your network or your Tailscale network. SparkDeck is an independent app. It is not affiliated with or endorsed by NVIDIA or ASUS. Terms of Use: https://sparkdeck.net/terms Privacy Policy: https://sparkdeck.net/privacy
LM Pocket
Run open-source AI models directly on your device without cloud reliance. Discover, download, and chat with thousands of GGUF models privately. Offers a local API server and advanced management tools for power users.
- Run open-source AI models locally
- Discover and download GGUF models
- Private, on-device conversations
- OpenAI-compatible local API server
- Manage model library and performance
- GPU acceleration for fast inference
Read full descriptionHide full description
Discover, download, and run open-source AI models directly on your device. No cloud. No subscription. No data leaves your device. LM Pocket brings the power of local AI models to your device. Browse thousands of GGUF models on Hugging Face, download them over WiFi, and chat with them entirely on-device. COMPLETELY PRIVATE Every conversation stays on your device. No server, no API key, no account required. Your prompts and responses never leave the device. DISCOVER MODELS Browse Hugging Face Hub for quantized GGUF models. Filter by size, quantization level, and popularity. See compatibility badges that tell you which models will run well on your device before downloading. CHAT WITH AI Stream token-by-token responses with full Markdown rendering. Manage multiple conversations. Adjust temperature, top-p, top-k, context length, and more. Supports ChatML, Llama, Mistral, Phi, Gemma, and other prompt formats automatically. LOCAL API SERVER Run an OpenAI-compatible HTTP server on your device. Expose /v1/chat/completions, /v1/models, and /v1/embeddings endpoints on your local network. Connect any app that supports the OpenAI API format. MANAGE YOUR LIBRARY Track installed models with storage usage. Import GGUF files from the Files app. Load and unload models with one tap. Monitor real-time performance: tokens per second, memory usage, and thermal state. BUILT FOR POWER USERS - GPU acceleration for fast inference - Background downloads with pause and resume - Hardware-aware model recommendations - Chat template auto-detection - Conversation export as JSON or Markdown - JSON mode with grammar-constrained output - Embeddings generation 100% FREE No subscriptions, no in-app purchases, no ads. Open-source AI should be accessible to everyone. SUPPORTED MODELS Run any GGUF-quantized model: Llama, Mistral, Phi, Gemma, CodeLlama, DeepSeek, Qwen, and thousands more from Hugging Face Hub. Model performance depends on device RAM and model size. Terms of Service: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/
Screenshots
Verdict
The clearest difference is in-app purchases: LM Pocket at none against SparkDeck's 2. LM Pocket also leads on update cadence (every 3 days vs every 6 months) and chart position (#209 vs unranked). SparkDeck's advantage is iOS requirement (18.0 vs 26.0). On price, ads 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
Both are free to download. SparkDeck sells 2 in-app purchases, starting at $3.99 per month. LM Pocket asks for nothing beyond the download.
SparkDeck ships an update every 6 months, LM Pocket every 3 days. The most recent releases landed on November 15, 2026 and November 18, 2026 respectively.
| Parameter | SparkDeck | LM Pocket |
|---|---|---|
| Price | Free | Free |
| Rating | — | 5.0 (3 ratings) — better |
| Number of ratings | — | 3 — better |
| Update frequency | Every 6 months | Every 3 days — better |
| Ads | No | No |
| In-app purchases | Yes | No — better |
| Monetization | — | Free |
| Best chart rank | — | #209 — better |
| Devices | iPhone | iPhone |
| Requires iOS | 18.0 — better | 26.0 |
| Further details — not scored | ||
| Size | 16 MB | 19 MB |
| Age rating | 4+ | 4+ |
| Developer | Yunus Sahin | Teo Bouancheau |
In-app purchases
SparkDeck
- Pro Monthly$3.991 Month
- Pro Yearly$29.991 Year
LM Pocket
No in-app purchases









