53 open-source models selected for local deployment. Each with its use case, the memory it needs and how to install it.
Source: Hugging Face and Ollama. Sizes checked on 6 October 2026.
53 models 8 categories 20 machines compared
Pick a model and a quantisation to see which machines it fits.
Pick a model, a quantisation and a context. The bars show which machines it fits.
Estimated memory needed
Weights = parameters × bits per weight ÷ 8 (Q4_0 4.5 · Q4_K_M 4.85 · Q8_0 8.5 · FP16 16). Cache = MB per token × context tokens. Runtime = 1.5 GB.
Measured with ollama ps on our GB10, real use comes in 1.4 to 1.6 GB below this figure: we would rather you have memory to spare than run short. From each machine we also take off the share the operating system keeps.
Estimated speed: –
From least to most memory. Open a machine for its spec sheet and where to buy it.
Tip:
Get this analysis by email
Analysis saved. We will email it to you.
Next step: Hardware selector ROI calculator Grants
53 models
Click a model for details
Best open coding model at 32B class. Strong at Python, JS, Go. Apache 2.0.
Mac Mini M4 Pro 48GB (Q8) or RTX 4090 24GB (Q4)
ollama pull qwen2.5-coder:32b Best small coding model. Fits on any device. Fast enough for real-time autocomplete.
Jetson Orin Nano 8GB (Q4) or any 16GB device (Q8)
ollama pull qwen2.5-coder:7b MoE with 21B active. Near GPT-4 coding quality. Best via API ($0.14/$0.28 per 1M).
Cloud API recommended
ollama pull deepseek-coder-v2 Trained on The Stack v2. Great for autocomplete. Supports 600+ programming languages.
Mac Mini M4 24GB (Q8) or a 12GB+ GPU (Q4)
ollama pull starcoder2:15b Proven and stable. Strong at Python, C++, Java. Good for production use where stability matters.
Mac Mini M4 Pro 48GB (Q8) or RTX 4090 24GB (Q4)
ollama pull codellama:34b Best open vision model for image understanding. Can describe images, answer questions about photos, read documents.
Mac Mini M4 Pro 48GB (Q8) or RTX 4090 (Q4)
ollama pull llava:34b Edge-optimized multimodal. Runs on phones and Jetson. Audio, video, image, text: all in 4B params.
Jetson Orin Nano 8GB or phone
ollama pull gemma3n:e4b Understands video, multiple images, and documents. Agent-ready with tool use. Apache 2.0.
Mac Studio 64GB+ or DGX Spark 128GB (Q4)
ollama pull qwen2.5-vl:72b Top-tier on chart/diagram understanding benchmarks. MIT license. Strong OCR.
Cloud or multi-GPU
ollama pull internvl2.5:78b Tiny (0.77B) but excellent at CV tasks. Runs on any device. MIT license. Perfect for edge vision.
Any device (even Raspberry Pi)
ollama pull florence2 Smallest practical vision model. Runs on Jetson, RPi, phones. Apache 2.0. Great for IoT vision.
Jetson Orin Nano, RPi 5, any device
ollama pull moondream Industry standard for semantic search. 384 dimensions. Blazing fast. We use this in Vorlux AI RAG system.
Any device (22M params = negligible VRAM)
ollama pull all-minilm:l6-v2 No models found
Select 2-3 models for a side-by-side comparison.
For jobs that need a bigger model than your machine holds, this is what the API costs. We only publish prices we have checked on each provider's official page.
| Model | Provider | Input | Output | Context |
|---|---|---|---|---|
| GPT-5 | OpenAI | $1.25 | $10.00 | 400K |
| GPT-5 Mini | OpenAI | $0.25 | $2.00 | 400K |
| Claude Sonnet 5 | Anthropic | $2.00 | $10.00 | 200K |
| Claude Haiku 4.5 | Anthropic | $1.00 | $5.00 | 200K |
Sources: OpenAI · Anthropic. To compare with what it costs locally, use the cost calculator.
Subscribe and we tell you when new guides, templates and workflows go up. One email a week, no spam.
Already published: 79 guides and 25 templates. All free, no signup.
Tell us what you want to run and on what budget. We will tell you which hardware you need, which model fits, and what to expect from it, before you spend anything.
79 free guides · 17 compliance templates
Your question, with your email; we answer it ourselves
Your question and your email:
What brings you here?