Best small open models you can run on a laptop

You do not need a server to run a good open model. These models fit in 16 to 32 GB of memory, or less, and cover chat, reasoning, coding and vision. The memory figures are our estimates at 4-bit precision for the smallest variant, except for models shipped in a lower-bit format, where we quote the file size.

  • List updated November 11, 2026
  1. Gemma 4

    Google's Apache 2.0 family has sizes for almost any machine: phone-sized E2B and E4B, a 12B, a 26B mixture of experts that activates 3.8B, and a 31B flagship. The smallest needs about 3.5 GB at 4-bit by our estimate.

    • Google DeepMind
    • 30.7B
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 3.52 GB
  2. gpt-oss

    The 21B version of OpenAI's Apache 2.0 reasoning model fits a 16 GB machine because only 3.6B parameters are active per token. It is from 2025, but nearly every local tool supports it.

    • OpenAI
    • 117B (5.1B active)
    • 128K tokens
    • Apache 2.0 (Permissive)
    • from 15 GB
  3. Qwen3.5

    Alibaba's Apache 2.0 family has small sizes at 0.8B, 2B, 4B and 9B next to larger ones, all with image and video input and a 256K context. By our estimate the 0.8B needs about 0.6 GB and the 9B about 7 GB at 4-bit.

    • Alibaba Qwen
    • 403B (17B active)
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 0.602 GB
  4. Qwen3.6

    A 35B mixture of experts that activates only 3B per token, and a 27B dense model, both under Apache 2.0 and tuned for agentic coding. By our estimate they need about 25 GB and 19 GB at 4-bit, so they suit a 32 GB machine.

    • Alibaba Qwen
    • 36B (3B active)
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 19 GB
  5. Laguna XS 2.1

    Poolside's 33B coding model that activates only 3B parameters per token. The official Q4_K_M file is 20.3 GB and the card says a Mac with 36 GB can run it, but it warned about llama.cpp, vLLM and Ollama rough edges, so check the current state first.

    • Poolside
    • 33.4B (3B active)
    • 256K tokens
    • OpenMDW-1.1 (Permissive)
    • from 22 GB
  6. GLM-4.7-Flash

    Z.ai's MIT-licensed 30B mixture of experts that activates 3B parameters per token. Official weights are 62.5 GB in BF16 only, so run a community 4-bit build, which needs about 22 GB by our estimate, on a 32 GB Mac or a 24 GB GPU.

    • Z.ai (Zhipu AI)
    • 31.2B (3B active)
    • 198K tokens
    • MIT (Permissive)
    • from 22 GB
  7. Raon-1 mini preview

    KRAFTON's 28.8B mixture of experts activates only 4.3B parameters per token and was trained from scratch for Korean chat and agents. By our estimate it needs about 18 GB at 4-bit, and its 17.6 GB NVFP4 build fits one 32 GB GPU. Apache 2.0, and the card calls it a preview.

    • KRAFTON
    • 28.8B (4.3B active)
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 18 GB
  8. Nemotron 3 Nano 4B

    NVIDIA's 4B Mamba-Transformer hybrid, compressed from Nano 9B v2, with switchable reasoning for RTX PCs and Jetson boards. By our estimate it needs under 3 GB at 4-bit.

    • NVIDIA
    • 3.97B
    • 256K tokens
    • NVIDIA Nemotron (Permissive)
    • from 2.74 GB
  9. GigaChat 3.1 Lightning

    Sber's MIT-licensed 10B mixture of experts with 1.8B active parameters, strong in Russian. The FP8 files are 12.3 GB and a Q4_K_M GGUF is 6.5 GB, but all 10B parameters must still fit in memory.

    • Sber (GigaChat)
    • 11.5B (1.8B active)
    • 256K tokens
    • MIT (Permissive)
    • from 7.15 GB
  10. Dory 1.0

    NVIDIA's 4B looped model: you choose whether its shared block runs one to four times, trading speed for quality from one checkpoint. It is about 8 GB in BF16 and 3.2 GB in NVFP4, with a 3.7 GB GGUF, and OpenMDW-1.1 allows commercial use.

    • NVIDIA
    • 4B
    • 256K tokens
    • OpenMDW-1.1 (Permissive)
    • from 2.76 GB
  11. Nanbeige4.2-3B

    BOSS Zhipin's 3B-class agent model (4.17B parameters with embeddings) under Apache 2.0, with a 256K context. Its own table reports 63.6 on SWE-bench Verified against 53.1 for Qwen3.5-9B, but it needs Nanbeige's forks of vLLM, SGLang or llama.cpp. By our estimate it needs about 3 GB at 4-bit.

    • Nanbeige LLM Lab
    • 4.17B
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 2.88 GB
  12. S5-nano

    Maritaca AI's 4B model built on Qwen3.5-4B for Brazilian Portuguese, with Think and Instruct modes, tool calling and a 256K context, under Apache 2.0. The Q4_K_M GGUF is 2.8 GB, and the benchmark scores are Maritaca's own.

    • Maritaca AI
    • 4.66B
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 3.08 GB
  13. Spark-X2.6

    TokenSpark's 1.7B and 4B models under Apache 2.0, with switchable thinking and a 1M-token position limit, though a context that long needs a lot of memory. The 4B is 3.41 GB in INT4, and its GGUF repository had about 660,000 downloads in the 30 days to 11 November 2026. The benchmark charts are TokenSpark's own.

    • TokenSpark (SparkLLM)
    • 4.11B
    • 1M tokens
    • Apache 2.0 (Permissive)
    • from 1.18 GB
  14. Raon-1 nano

    KRAFTON's 3.1B on-device model (1.5B effective), distilled from its larger mixture of experts for Korean and English with tool calling and a 262K context. The 4-bit GGUF is 2.1 GB, and MLX and LiteRT-LM builds are about 1.8 GB. Apache 2.0, and every score is KRAFTON's own.

    • KRAFTON
    • 3.1B
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 1.98 GB
  15. MiniCPM5-2B

    A dense 2B model for phones and laptops with a 128K context, tool use and coding, under Apache 2.0, and OpenBMB released its training data. A 1B version is also available.

    • OpenBMB
    • 2.52B
    • 128K tokens
    • Apache 2.0 (Permissive)
    • from 0.745 GB
  16. Ternary Bonsai 2

    PrismML's Qwen-based models with ternary weights and vision: a 27B-class model in 5.95 GB and a 2B model in 0.43 GB, under Apache 2.0. Some of the file formats need PrismML's llama.cpp fork.

    • PrismML
    • 27.4B
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 0.473 GB
  17. LFM2.5-24B-A2B

    A 24B mixture of experts that activates only 2.45B parameters per token, so it generates quickly. It needs about 17 GB at 4-bit by our estimate, and the license is free only below US$10 million of revenue.

    • Liquid AI
    • 24B (2.45B active)
    • 128K tokens
    • LFM Open 1.0 (Conditional)
    • from 17 GB
  18. Granite 4.2

    IBM's dense reasoning family in 3B, 8B and 30B sizes, with switchable thinking and tool calling, under Apache 2.0 and aimed at enterprise use.

    • IBM
    • 29.3B
    • 128K tokens
    • Apache 2.0 (Permissive)
    • from 2.55 GB
  19. Mellum2.1

    JetBrains' 12B mixture of experts with 2.5B active parameters, built for coding agents, under Apache 2.0. JetBrains publishes 8.1 GB 4-bit and 7.0 GB MXFP4 files, and its own table shows Qwen3.5-9B ahead on SWE-bench Verified (50.0 against 47.0).

    • JetBrains
    • 12.2B (2.5B active)
    • 128K tokens
    • Apache 2.0 (Permissive)
    • from 7.7 GB
  20. Olmo 3.1

    Ai2's fully open 7B and 32B models: weights, training data, code and checkpoints are all public, under Apache 2.0. The 7B needs about 5 GB at 4-bit by our estimate.

    • Allen Institute for AI (Ai2)
    • 32.2B
    • 64K tokens
    • Apache 2.0 (Permissive)
    • from 5.04 GB
  21. K2 Horizon

    IFM's family has a 7B (5.6 GB as 4-bit GGUF), a 3.7B (3.2 GB) and a 0.9B (0.67 GB) under Apache 2.0, with a 512K context (128K for the 0.9B), plus a 36B-A4B that needs about 22 GB in 4-bit. GGUF files need a recent llama.cpp, and in IFM's own table the 7B scores 72.4 on SWE-bench Verified against 50.8 for Qwen3.5-9B.

    • Institute of Foundation Models (MBZUAI)
    • 379B (23B active)
    • 512K tokens
    • Apache 2.0 (Permissive)
    • from 0.745 GB
  22. Jais 3

    The Arabic-first branch of K2 Horizon, with 0.9B, 3.7B and 7B models for phones and laptops (the 7B is 5.6 GB as 4-bit GGUF) and a 36B-A4B for a workstation. IFM's own tests put the 7B at 79.4 on Arabic against 76.9 for Gemma 4 12B.

    • Institute of Foundation Models (MBZUAI)
    • 379B (23B active)
    • 512K tokens
    • Apache 2.0 (Permissive)
    • from 0.745 GB
  23. LFM3

    Liquid AI's 2B-class family: a 1.7B text model with a 256K context that fits in about 1 GB, plus vision, audio and omni siblings. The license is free only below US$10 million of revenue.

    • Liquid AI
    • 2.17B
    • 256K tokens
    • LFM Open 1.0 (Conditional)
    • from 1.19 GB
  24. MiniCPM-V 4.7

    OpenBMB's vision-language models for images and video: a 1B model that runs on a phone, and a 35B mixture of experts that activates 3B. Apache 2.0.

    • OpenBMB
    • 35.2B (3B active)
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 1.07 GB
  25. MiniCPM-o 4.5

    OpenBMB's 9B model for live video and voice chat, with an 8.5 GB AWQ int4 build, a 12 GB GPU for llama.cpp-omni and Apple silicon support. Speech is English and Chinese.

    • OpenBMB
    • 9.37B
    • 40K tokens
    • Apache 2.0 (Permissive)
    • from 11 GB
  26. Mage-VL

    Microsoft's 4B vision-language model for images, long video and live streams, under Apache 2.0. It reads video like a codec, cutting visual tokens by more than 75%, and Microsoft's tables put it ahead of Qwen3-VL-4B on most video tests. By our estimate it needs about 3 GB at 4-bit.

    • Microsoft
    • 4.74B
    • 256K tokens
    • Apache 2.0 (Permissive)
    • from 3.27 GB

How we chose

  • The smallest variant runs in roughly 16 GB of memory or less, or the model activates few parameters per token.
  • The license allows use by most individuals and small companies; the entry notes where it does not.
  • Weights are available today on Hugging Face and supported by common local tools.