Runs 7B models — Refurbished devices
275 refurbished laptops, desktops & mini PCs for running Ollama, LM Studio, Llama 3, Qwen, and Mistral locally — no cloud, no API key. Ships same day from Reno, NV.
Filter by AI capability
Filters
275 devices · Laptop · Runs 7B models
HP
HP ENVY 17-cr0797nr 17.3"FHD TOUCH i7-1255U 1.7GHz 16GB 1TB SSD Win 11 Home +PA
Dell
Dell Latitude 7340 2n1 13.3" QHD+ Touch i7-1365U 16GB 256GB SSD WRNTY Win11P+PA
ASUS
ASUS VivoBook M3704YA-IS74 17.3”FHD AMD Ryzen 7 7730U 2GHz 24GB 1TB Win 11Home
Dell
Dell Latitude 5550 15.6" FHD Ultra 7 155U 16GB 512GB SSD Win 11Pro PWR Battery
Microsoft
Microsoft Surface Laptop 6 15" Touch Ultra 5 135H 16GB 512GB SSD W11P + Charger
Dell
Dell Pro 14 Plus PB14250 14"FHD+ core Ultra 5 236V 16GB 512GB SSD Windows 11 PRO
Lenovo
Lenovo Yoga 7 16IML9 16"WUXGA TOUCH Ultra 7 155U 1.7GHz 16GB 1TB Windows 11 Home
Lenovo
Lenovo Slim 7 Carbon 13IAP7 13.3" WQXGA TOUCH i7-1260P 2.1GHz 16GB 1TB W11H +PA
Dell
Dell Latitude 5550 15.6" FHD Ultra 7 155U 1.70GHz 16GB 512GB SSD WRNTY Win11P+PA
ASUS
ASUS Vivobook S14 K5404VA 14" 120hz OLED intel i9-13900H 2.6GHz 16GB 1TB +PA
Dell
Dell Precision 3580 15.6"FHD i5-13 1.9GHz 16GB 512GB SSD RTX A500 WRTY-11/26 +PA
Microsoft
Microsoft Surface Laptop 7th Edition 15" TOUCH Snapdragon X 16GB 256GB 100%BATT
Microsoft
Microsoft Surface Laptop 6 15" Touch Ultra 5 135H 16GB 512GB SSD Win11Pro+PA
ASUS
ASUS Vivobook S14 S5406MA 14" OLED ULTRA 9 185H 2.5GHz 16GB 1TB Win 11 PRO +PA
Lenovo
Lenovo ThinkPad X1 Carbon Gen 11 14"FHD+ TOUCH i7-1355U 16GB 512GB Win11Pro +PA
Dell
Dell Precision 5570 15.6"FHD+ RTX A2000 8GB i7-12800H 16Gb 512GB WRTY 08/2028
Lenovo
Lenovo ThinkPad E16 G2 16" FHD+ Touch 7 7735U 2.70GHz 16GB 512GB WRNTY Win11P+PA
Dell
Dell Latitude 7650 16" FHD+ Ultra 7 165H 3.8GHz 16GB 512GB SSD WRNTY-09/27 +PA
Dell
Dell Pro 14 Plus PB14250 14"FHD+ Ultra 5 236V 16GB 512GB Warranty 2027 Win 11PRO
Dell
Dell Pro 14 Plus PB14250 Ultra 5 236V 16GB 512GB FHD+ W11P WTY08/27+65W Dell PA
Dell
Dell Pro 14 Plus PB14250 Intel Core Ultra 5 236V 16GB 14in vPro WTY08/27+Charger
HP
HP ENVY 17-da0013dx 17.3" FHD TOUCH Ultra 7 155H 16GB 1TB SSD Win 11 Home
Samsung
2026 SAMSUNG GALAXY BOOK 6 14"WUXGA Ultra 7 355 2.3Ghz 16GB 512GB Windows 11Home
HP
2026 HP OmniBook X FlipNGAI 14-kc0023dx 14" Touch AMD Ryzen AI 7 445 24GB 1TB
Lenovo
Lenovo Legion 5 Pro 16" WQXGA 165hz i7-11800H 2.3GHz 16GB 512GB RTX 3050 4GB
Lenovo
Lenovo ThinkPad X13 Gen 6 Intel Ultra 7 255U 16GB 512GB Win 11 Pro WARRANTY
Samsung
2026 SAMSUNG GALAXY BOOK 6 16"WUXGA TOUCH Ultra 7 355 2.3Ghz 16GB 512GB W11Home
Dell
Dell XPS 15 9530 i7-13700H 16GB 512GB A370M 15.6" Win11Pro WTY11/26+130W Dell PA
Dell
Dell Pro 16 Plus PB16250 16"FHD+ Ultra 7 265U 16GB 512GB SSD Win11Pro WRTY2028
HP
2026 HP ZBook 8 G1i Mobile Workstation 14"FHD+ Ultra 7 265H 2.1GHz 16GB 512GB
Dell
Dell Precision 5690 16"FHD+ Ultra 7 165H 16GB 512GB RTX 1000 ADA 6GB WRTY06/2027
HP
HP ZBook 8 G1i 14"FHD+ Ultra 7 265H 2.1GHz 16GB 512GB Win 11Pro Warranty 2030
Lenovo
NEW Lenovo ThinkPad P14s Gen 6 AMD 14"WUXGA Ryz AI 5 PRO 340 16GB RAM 512GB SSD
Dell
Dell Pro 16 Plus PB16250 Ultra 7 265U 16GB 512GB 16" FHD+ W11 Pro Warranty+PA
HP
HP Elitebook 8 G1i 14" Ultra 7 265U 64GB RAM 512GB Ultrabook Laptop 2029 WRTY
How to run AI locally
Pick a device
Filter by tier, brand, or type.
Install Ollama
Free. ollama.com. 2 minutes.
Pull a model
ollama run llama3
Chat privately
Nothing leaves your machine.
Common questions
What laptop do I need to run Llama 3.1 locally?
To run Llama 3.1 8B comfortably, you need at least 16GB RAM. For Llama 3.1 70B, you need 32GB+ RAM or a GPU with 16GB+ VRAM. Apple Silicon MacBooks (M1/M2/M3/M4) with 16GB unified memory run 8B models at 20–40 tokens/sec with no setup beyond installing Ollama.
Can I run local AI on a laptop without a GPU?
Yes. CPU-only inference works well for 7B–8B models on any laptop with 16GB+ RAM. Expect 5–15 tokens/sec, which is readable in real time. For faster speeds, a laptop with a discrete NVIDIA GPU (6GB+ VRAM) or Apple Silicon is recommended.
How much RAM do I need to run AI models locally?
8GB RAM is the minimum — runs Phi-4 Mini and Llama 3.2 3B only. 16GB RAM runs Llama 3.1 8B and Qwen3 7B at usable speeds. 32GB runs Qwen2.5 14B and 32B Q4 models. 64GB runs 70B models at full quality.
Do desktops and mini PCs work for local AI?
Yes. A Dell OptiPlex or Intel NUC with 16GB RAM runs 7B models well. Gaming desktops with RTX GPUs (8GB+ VRAM) handle 13B–32B models at 20–50 tokens/sec.
Is Apple Silicon (M1/M2/M3/M4) good for running local AI?
Apple Silicon is excellent for local AI. Unified memory means the GPU and CPU share the same RAM pool, so a 32GB M2 Pro can offload a full 32B model to the GPU. Metal acceleration is automatic via Ollama. M1 16GB runs 8B models at 20–30 tokens/sec. M2/M3/M4 32GB runs 32B Q4 models at 15–25 tokens/sec.
How do I start after buying a device?
Install Ollama from ollama.com (free, 2 minutes). Open Terminal and run: ollama run llama3.1:8b — it downloads the model and starts automatically. For a ChatGPT-style interface, install LM Studio from lmstudio.ai. No cloud account, no subscription, no data leaving your machine.