Home › Best › best local LLM for a laptop The best open LLMs for a laptop Open LLMs calculated against a conservative 6 GB memory budget at the stated default quant and context, leaving some headroom for an entry laptop GPU or shared-memory Mac. Ranked by popularity within that calculated set. Confirm the build against your laptop's available memory and runner before downloading.
How this is ranked: Transparent calculated filter at a conservative 6 GB budget. It is a shortlist, not a hardware guarantee or quality ranking. Exact fit and speed depend on available RAM/VRAM, the runner, quantization, context, and background system use.
1. Qwen3 0.6B — Qwen, 800M · ~3.0 GB VRAM · $0.11/1M API est. · commercial OK2. Qwen3 4B — Qwen, 4B · ~5.0 GB VRAM · $0.13/1M API est. · commercial OK3. Qwen2.5 3B Instruct — Qwen, 3.1B · ~4.0 GB VRAM · $0.12/1M API est. · non-commercial4. Llama 3.2 3B Instruct — Meta, 3B · ~5.0 GB VRAM · $0.19/1M API · commercial OK5. Qwen2.5 1.5B Instruct — Qwen, 1.5B · ~3.0 GB VRAM · $0.11/1M API est. · commercial OK6. gemma 3 270m — google, 300M · ~2.0 GB VRAM · $0.10/1M API est. · commercial OK7. Qwen3 1.7B — Qwen, 2B · ~5.0 GB VRAM · $0.12/1M API est. · commercial OK8. BGE-M3 — BAAI, 567M · ~3.0 GB VRAM · $0.10/1M API est. · commercial OK9. Qwen3 4B Instruct 2507 — Qwen, 4B · ~5.0 GB VRAM · $0.13/1M API est. · commercial OK10. Qwen2.5 0.5B Instruct — Qwen, 500M · ~2.0 GB VRAM · $0.10/1M API est. · commercial OK11. Qwen2 1.5B Instruct — Qwen, 1.5B · ~3.0 GB VRAM · $0.11/1M API est. · commercial OK12. Llama 3.2 1B Instruct — Meta, 1.2B · ~3.0 GB VRAM · $0.11/1M API · commercial OK13. Llama 3.2 1B — meta-llama, 1.2B · ~3.0 GB VRAM · $0.11/1M API est. · commercial OK14. Qwen2.5 0.5B — Qwen, 500M · ~2.0 GB VRAM · $0.10/1M API est. · commercial OK15. Phi-3.5-mini Instruct — Microsoft, 3.8B · ~5.0 GB VRAM · $0.13/1M API est. · commercial OK16. gemma 3 1b it — google, 1B · ~3.0 GB VRAM · $0.11/1M API est. · commercial OK17. TinyLlama 1.1B Chat v1.0 — TinyLlama, 1.1B · ~2.0 GB VRAM · $0.11/1M API est. · commercial OK18. Rio 3.0 Open Mini — prefeitura-rio, 4B · ~5.0 GB VRAM · $0.13/1M API est. · commercial OK19. gpt2 large — openai-community, 800M · ~2.0 GB VRAM · $0.11/1M API est. · commercial OK20. OpenELM 1 1B Instruct — apple, 1.1B · ~3.0 GB VRAM · $0.11/1M API est. · non-commercial21. PowerMoE 3b — ibm-research, 3.4B · ~4.0 GB VRAM · $0.13/1M API est. · commercial OK22. Phi 4 mini instruct — microsoft, 3.8B · ~6.0 GB VRAM · $0.22/1M API · commercial OK23. Qwen2.5 1.5B — Qwen, 1.5B · ~3.0 GB VRAM · $0.11/1M API est. · commercial OK24. NVIDIA Nemotron 3 Nano 4B BF16 — nvidia, 4B · ~6.0 GB VRAM · $0.13/1M API est. · non-commercial25. h2ovl mississippi 800m — h2oai, 800M · ~2.0 GB VRAM · $0.11/1M API est. · commercial OK26. h2ovl mississippi 2b — h2oai, 2.2B · ~4.0 GB VRAM · $0.12/1M API est. · commercial OK27. Nomic Embed Text v1.5 — Nomic AI, 137M · ~2.0 GB VRAM · $0.10/1M API est. · commercial OK28. Qwen2 0.5B — Qwen, 500M · ~2.0 GB VRAM · $0.10/1M API est. · commercial OK29. SmolLM 1.7B Instruct quantized.w4a16 — nm-testing, 1.8B · ~3.0 GB VRAM · $0.11/1M API est. · commercial OK30. Qwen2.5 1.5B quantized.w8a8 — RedHatAI, 1.8B · ~3.0 GB VRAM · $0.11/1M API est. · commercial OK31. Qwen2.5 Math 1.5B — Qwen, 1.5B · ~3.0 GB VRAM · $0.11/1M API est. · commercial OK32. gpt neo 2.7B — EleutherAI, 2.7B · ~4.0 GB VRAM · $0.12/1M API est. · commercial OK33. Llama 3.2 3B — meta-llama, 3.2B · ~5.0 GB VRAM · $0.13/1M API est. · commercial OK34. Qwen2 0.5B Instruct — Qwen, 500M · ~2.0 GB VRAM · $0.10/1M API est. · commercial OK35. Phi tiny MoE instruct — microsoft, 3.8B · ~4.0 GB VRAM · $0.13/1M API est. · commercial OK36. Qwen2.5 Coder 1.5B Instruct — Qwen, 1.5B · ~3.0 GB VRAM · $0.11/1M API est. · commercial OK37. Qwen2.5 Coder 3B — Qwen, 3.1B · ~4.0 GB VRAM · $0.12/1M API est. · non-commercial38. Qwen3 4B Base — Qwen, 4B · ~5.0 GB VRAM · $0.13/1M API est. · commercial OK39. Kimi K3 DSpark — RadixArk, 2.2B · ~3.0 GB VRAM · $0.12/1M API est. · non-commercial40. Qwen3 1.7B Base — Qwen, 1.7B · ~4.0 GB VRAM · $0.11/1M API est. · commercial OKShowing the top 40 of 170. See all →
More: all "best" lists · Outcome Lab · all models
Open the free LLM cost calculator → · $0 markup. © 2026 Cynosure LLC.