nowfound

AI · free · 2026

24 free alternatives to Qwen3.5 Small

0.8B-9B native multimodal w/ more intelligence, less compute

Qwen3.5 Small costs from $9/mo (its own site, checked November 2026). Below are 24 products that do a similar job and cost nothing to start: 18 free outright and 6 with a free plan and paid upgrades. Each price was read from the product's own site. They are ranked by how close each is in meaning, then by launch-day votes.

  1. 1

    Last week was big for open source LLMs. We got: - Qwen 2.5 VL (72b and 32b) - Gemma-3 (27b) - DeepSeek-v3-0324 And a couple weeks ago we got the new mistral-ocr model. We updated our OCR benchmark to include the new models. We evaluated 1,000 documents for JSON extraction accuracy. Major takeaways: - Qwen 2.5 VL (72b and 32b) are by far the most impressive. Both landed right around 75% accuracy (equivalent to GPT-4o’s performance). Qwen 72b was only 0.4% above 32b. Within the margin of error. - Both Qwen models passed mistral-ocr (72.2%), which is specifically trained for OCR. - Gemma-3…

    2025 · github.com · price checked November 2026

  2. 2
    Qwen2.5-OmniFree▲165

    The end-to-end model powering multimodal chat

    2025 · github.com · price checked November 2026

  3. 3
    Qwen3Free▲149

    Think Deeper or Act Faster

    2025 · github.com · price checked November 2026

  4. 4
    Qwen3.8-Flash-NextFree plan▲108

    The open-weight preview of Qwen4

    Aug 2026 · qwen.ai · price checked September 2026

  5. 5
    Qwen3-OmniFree▲137

    Native end-to-end multilingual omni-modal LLM

    2025 · github.com · price checked November 2026

  6. 6
    Z80-μLMFree▲514

    Z80-μLM is a character-level language model compressed into a 40KB file that runs on a Z80 processor with 64KB RAM, executable in CP/M emulators or on vintage hardware.

    Dec 2025 · github.com · price checked November 2026

  7. 7
    guppylmFree▲915

    Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.

    Apr 2026 · github.com · price checked November 2026

  8. 8

    This project replicates mechanistic interpretability research on large language models using sparse autoencoders, building on published work from Anthropic, OpenAI, and DeepMind.

    2024 · github.com · price checked November 2026

  9. 9
    Conversational AI 2.0 From ElevenLabsFree plan, paid from $6/mo▲652

    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 · price checked November 2026

  10. 10

    Metal-first MoE inference for Apple Silicon with bounded SSD expert streaming and local OpenAI Chat, Responses, and Anthropic Messages endpoints.

    Jul 2026 · github.com · price checked November 2026

  11. 11

    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.

    Aug 2026 · github.com · price checked November 2026

  12. 12

    This project documents efforts to run GLM 5.2, a large language model comparable to Claude or GPT, on standard consumer hardware with limited resources.

    Jul 2026 · github.com · price checked November 2026

  13. 13

    This project enables running the Qwen3-Next-80B model on a graphics card with only 8GB of memory, achieving approximately one token per two seconds of processing speed.

    2025 · github.com · price checked November 2026

  14. 14
    NeedleFree▲776

    Needle is a 26-million-parameter open-source model designed for function calling and tool use on consumer devices like phones and watches.

    May 2026 · github.com · price checked November 2026

  15. 15

    An educational Rust project for exporting and running inference on Qwen3 LLM family

    2025 · github.com · price checked November 2026

  16. 16

    SlotStream enables users to run the Qwen3.8-Flash-Next 125B mixture-of-experts model on Mac computers with limited RAM by streaming model components from storage to memory as needed.

    Sep 2026 · github.com · price checked November 2026

  17. 17
    Tiny-vLLMFree▲205

    Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM

    May 2026 · github.com · price checked November 2026

  18. 18
    Eleven v3 (alpha)Free plan, paid from $6/mo▲401

    The most expressive Text to Speech model ever

    2025 · elevenlabs.io · price checked November 2026

  19. 19

    This project provides an optimized implementation for finetuning Llama models using QLoRA and LoRA techniques on local GPUs.

    2023 · github.com · price checked November 2026

  20. 20
    QwenImage3Free plan, paid from $8/mo▲4

    AI image generation from text prompts made simple

    Jul 2026 · qwenimage3.org · price checked November 2026

  21. 21

    The Swiss Army Knife of Offline AI.

    Mar 2026 · github.com · price checked November 2026

  22. 22
    Lightning V3Free plan, paid from $1000/mo▲311

    Add AI Voice & Chat Agents directly to your website.

    Apr 2026 · smallest.ai · price checked November 2026

  23. 23
    Willow Frontier ProFree plan▲278

    Willow Frontier Pro is a dictation model designed for users who need fast and accurate voice-to-text conversion for writing tasks.

    Jul 2026 · willowvoice.com · price checked November 2026

  24. 24

    Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

    Aug 2026 · github.com · price checked November 2026

Free tools by topic

All alternatives to Qwen3.5 Small, paid too →About Qwen3.5 Small →

Free means the product’s own site says it is free or offers a free plan, as read on the date shown. Plans change; check the site before you rely on one.