Life & fun · alternatives · 2026
24 alternatives to Maple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhone
Maple-Preview is a large language model that runs directly on iPhones, delivering inference speeds of 120 tokens per second. Built on a ternary 20 billion parameter mixture-of-experts architecture, it enables users to… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes. Prices are shown for the 1 we have checked on their own sites, 1 of them free or with a free tier.
- 1
Ollama v0.19▲410Massive local model speedup on Apple Silicon with MLX
Apr 2026 · ollama.com · its alternatives →
- 2
Swiftlet is a Swift and Metal runtime that runs large Qwen Mixture-of-Experts models locally on Apple devices by streaming expert weights from storage, enabling 35B and 80B models to run with low RAM, including on iPhone. - leonickson1/Swiftlet
Aug 2026 · github.com · its alternatives →
- 3
Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
2025 · github.com · its alternatives →
- 4
Luke from ElevenLabs here. We just released Scribe Realtime v2, our new real-time Speech to Text model. We rebuilt it from the ground up around a new architecture that uses predictive transcription – it anticipates the next likely word before it’s spoken. That makes it both fast (around 150 ms latency) and highly accurate. Scribe v2 Realtime outperforms every low latency transcription model across 30 commonly used EU and Asian languages – 93.5% accuracy, compared to Gemini 2.5 Flash (91.4%), GPT-4o MiniTranscribe (90.7%), and Deepgram Nova 3 (85%). It supports 90+ languages including…
2025 · elevenlabs.io · its alternatives →
- 5
First TTS model to support all 22 Indic languages + English
2024 · its alternatives →
- 6
MiMo-V2-Flash▲241Ultra-fast 309B MoE model for coding & agents
Dec 2025 · mimo.xiaomi.com · its alternatives →
- 7
- 8
Daytona ▲453Secure and elastic infra for running your AI-generated code.
2025 · daytona.io · its alternatives →
- 9
Pinch▲535Hey HN! I’m Christian, daily lurker and some might remember our original launch post (https://news.ycombinator.com/item?id=42935355). Today we're launching Pinch for Mac, which we believe is a step-change improvement in real-time AI translation. Our vision is to make cross-lingual conversations feel as natural as regular conversations. TL:DR During an online meeting, the app instantly transcribes and translates all audio you hear, and allows you to decide when you translate your voice and when you don't. It's invisible to others (like Granola), and works everywhere without any…
2025 · startpinch.com · its alternatives →
- 10
How small can a language model be while still doing something useful? I wanted to find out, and had some spare time over the holidays. Z80-μLM is a character-level language model with 2-bit quantized weights ({-2,-1,0,+1}) that runs on a Z80 with 64KB RAM. The entire thing: inference, weights, chat UI, it all fits in a 40KB .COM file that you can run in a CP/M emulator and hopefully even real hardware! It won't write your emails, but it can be trained to play a stripped down version of 20 Questions, and is sometimes able to maintain the illusion of having simple but terse conversations…
Dec 2025 · github.com · its alternatives →
- 11
Lightning V3▲311Add AI Voice & Chat Agents directly to your website.
Apr 2026 · smallest.ai · its alternatives →
- 12
Qwen3.6-35B-A3B▲124The open sparse MoE model for agentic coding
Apr 2026 · qwen.ai · its alternatives →
- 13
DeepSeek-V4▲387The open-source era of 1M context intelligence
Apr 2026 · huggingface.co · its alternatives →
- 14
Willow on IOS▲395Write 5x faster with voice dictation now Available on iOS
Nov 2025 · apps.apple.com · its alternatives →
- 15
- 16
Qwen3.5▲288The 397B native multimodal agent with 17B active params
Feb 2026 · qwen.ai · its alternatives →
- 17
We wrote our inference engine on Rust, it is faster than llama cpp in all of the use cases. Your feedback is very welcomed. Written from scratch with idea that you can add support of any kernel and platform.
2025 · github.com · its alternatives →
- 18
Qwen3.5 Small▲3550.8B-9B native multimodal w/ more intelligence, less compute
Mar 2026 · huggingface.co · its alternatives →
- 19
Blazing fast keyboard for iOS now with GIFs and more
2016 · apps.apple.com · its alternatives →
- 20
Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference code. One command to load, one command to serve. 336x faster than Python inference. - kossisoroyce/timber
Mar 2026 · github.com · its alternatives →
- 21
Metal-first MoE inference for Apple Silicon with bounded SSD expert streaming and local OpenAI Chat, Responses, and Anthropic Messages endpoints. - hebrus-labs/hebrus
Jul 2026 · github.com · its alternatives →
- 22
Qwen3.8-Flash-Nextfree tier▲108The open-weight preview of Qwen4
Aug 2026 · qwen.ai · its alternatives →
- 23
We took a recently released Bonsai 1.7B ternary model from PrismML (https://github.com/PrismML-Eng/Bonsai-demo) and ran our agentic evolution search on it for 6 hours to optimize the Metal kernels. The search was fully autonomous. Measured against unmodified upstream llama.cpp at the same Bonsai/Q2_0 commit, same M4 Max: - tg128: 309.82 → 442.42 t/s (+42.0%) - pp512: 4250.32 → 4622.63 t/s (+8.8%)
May 2026 · agents2agents.ai · its alternatives →
- 24
Explore large language models in 512MB of RAM. Contribute to jncraton/languagemodels development by creating an account on GitHub.
2023 · github.com · its alternatives →
Also compare
Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →