RTX 4060 8 GB
Budget8 GB VRAM · ~7.2 GB for a model
NVIDIA GeForce RTX 4060 8 GB
- Qwen2.5-1.5B-Instruct~164 tok/s
- Llama-3.2-1B-Instruct~185 tok/s
- gemma-3-1b-it~204 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →Best hardware for running AI at home
The one spec that decides which AI models you can run at home is memory: VRAM on a graphics card, or unified memory on a Mac. Each card shows the most downloaded open models that fit and their estimated speed.
As an Amazon Associate we earn from qualifying purchases. Prices change often, so we link to Amazon instead of listing them.
Graphics cards
For a desktop PC. VRAM decides which models fit; more of it runs bigger models.
RTX 3060 12 GB
Budget12 GB VRAM · ~10.8 GB for a model
NVIDIA GeForce RTX 3060 12 GB
- Qwen3.5-4B~91 tok/s
- Qwen2.5-1.5B-Instruct~188 tok/s
- Qwen2.5-3B-Instruct~116 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →
12 GB VRAM · ~10.8 GB for a model
NVIDIA GeForce RTX 4070 12 GB
- Qwen3.5-4B~131 tok/s
- Qwen2.5-1.5B-Instruct~259 tok/s
- Qwen2.5-3B-Instruct~165 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →
24 GB VRAM · ~21.6 GB for a model
NVIDIA GeForce RTX 3090 24 GB
- Llama-3.1-8B-Instruct~123 tok/s
- Qwen3-8B~117 tok/s
- Qwen2.5-7B-Instruct~135 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →
RTX 4090 24 GB
High-end24 GB VRAM · ~21.6 GB for a model
NVIDIA GeForce RTX 4090 24 GB
- Llama-3.1-8B-Instruct~139 tok/s
- Qwen3-8B~133 tok/s
- Qwen2.5-7B-Instruct~153 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →
RTX 5090 32 GB
High-end32 GB VRAM · ~28.8 GB for a model
NVIDIA GeForce RTX 5090 32 GB
- Llama-3.1-8B-Instruct~222 tok/s
- Qwen3-8B~213 tok/s
- Qwen3.5-9B~225 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →Macs
Apple silicon shares one pool of unified memory between the chip and the GPU, so a model can use most of it.
MacBook Air with 16 GB
Budget16 GB unified memory · ~11.2 GB for a model
M5, 10-core GPU
- Qwen3.5-4B~46 tok/s
- Qwen2.5-1.5B-Instruct~109 tok/s
- Qwen2.5-3B-Instruct~61 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →
Mac mini with 16 GB
Budget16 GB unified memory · ~11.2 GB for a model
M4
- Qwen3.5-4B~35 tok/s
- Qwen2.5-1.5B-Instruct~82 tok/s
- Qwen2.5-3B-Instruct~45 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →Mac mini with 24 GB
Budget24 GB unified memory · ~16.8 GB for a model
M4
- Qwen3.5-4B~35 tok/s
- Qwen2.5-3B-Instruct~45 tok/s
- Llama-3.2-3B-Instruct~38 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →24 GB unified memory · ~16.8 GB for a model
M5, 10-core GPU
- Qwen3.5-4B~46 tok/s
- Qwen2.5-3B-Instruct~61 tok/s
- Llama-3.2-3B-Instruct~51 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →32 GB unified memory · ~22.4 GB for a model
M5, 10-core GPU
- Llama-3.1-8B-Instruct~26 tok/s
- Qwen3-8B~24 tok/s
- Qwen3.5-9B~26 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →
Mac Studio with 64 GB
High-end64 GB unified memory · ~44.8 GB for a model
M4 Max, 40-core GPU
- Llama-3.1-8B-Instruct~74 tok/s
- Qwen3-8B~70 tok/s
- Qwen3.5-9B~75 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →Mac Studio with 128 GB
High-end128 GB unified memory · ~89.6 GB for a model
M4 Max, 40-core GPU
- Qwen3.8-27B~25 tok/s
- gemma-4-31B-it~21 tok/s
- gpt-oss-20b~92 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →Powerful laptops
Gaming laptops with NVIDIA GPUs and MacBook Pros that run local models on the go.
8 GB VRAM · ~7.2 GB for a model
NVIDIA GeForce RTX 4070 Laptop GPU 8 GB
- Qwen2.5-1.5B-Instruct~164 tok/s
- Llama-3.2-1B-Instruct~185 tok/s
- gemma-3-1b-it~204 tok/s
Speeds estimated from the desktop RTX 4060; expect somewhat less on a laptop.
Buy on AmazonCheck price on Amazon
All models for this device →
24 GB unified memory · ~16.8 GB for a model
M4 Pro, 20-core GPU
- Qwen3-4B~10 GB
- Qwen3.5-4B~10 GB
- Ornith-1.5-9B-GGUF~6 GB
Buy on AmazonCheck price on Amazon
All models for this device →
RTX 4090 Laptop 16 GB
High-end16 GB VRAM · ~14.4 GB for a model
NVIDIA GeForce RTX 4090 Laptop GPU 16 GB
- Qwen3-4B~10 GB
- Qwen3.5-4B~10 GB
- Ornith-1.5-9B-GGUF~6 GB
Speeds estimated from the desktop RTX 4080; expect somewhat less on a laptop.
Buy on AmazonCheck price on Amazon
All models for this device →
RTX 5090 Laptop 24 GB
High-end24 GB VRAM · ~21.6 GB for a model
NVIDIA GeForce RTX 5090 Laptop GPU 24 GB
- Llama-3.1-8B-Instruct~139 tok/s
- Qwen3-8B~133 tok/s
- Qwen2.5-7B-Instruct~153 tok/s
Speeds estimated from the desktop RTX 4090; expect somewhat less on a laptop.
Buy on AmazonCheck price on Amazon
All models for this device →MacBook Pro with 36 GB
High-end36 GB unified memory · ~25.2 GB for a model
M5 Max, 32-core GPU
- Llama-3.1-8B-Instruct~68 tok/s
- Qwen3-8B~64 tok/s
- Qwen3.5-9B~69 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →MacBook Pro with 48 GB
High-end48 GB unified memory · ~33.6 GB for a model
M5 Pro, 20-core GPU
- Llama-3.1-8B-Instruct~51 tok/s
- Qwen3-8B~48 tok/s
- Qwen3.5-9B~51 tok/s
Buy on AmazonCheck price on Amazon
All models for this device →MacBook Pro M4 Max with 48 GB
High-end48 GB unified memory · ~33.6 GB for a model
M4 Max, 40-core GPU
- Llama-3.1-8B-Instruct~20 GB
- Qwen3-8B~20 GB
- Qwen3.5-9B~22 GB
Buy on AmazonCheck price on Amazon
All models for this device →Compare at a glance
| Device | Type | Memory | Usable | Budget | Shop |
|---|---|---|---|---|---|
| RTX 4060 8 GB | Graphics cards | 8 GB VRAM | ~7.2 GB | Budget | Check price |
| RTX 3060 12 GB | Graphics cards | 12 GB VRAM | ~10.8 GB | Budget | Check price |
| RTX 4070 12 GB | Graphics cards | 12 GB VRAM | ~10.8 GB | Mid | Check price |
| RTX 3090 24 GB | Graphics cards | 24 GB VRAM | ~21.6 GB | Mid | Check price |
| RTX 4090 24 GB | Graphics cards | 24 GB VRAM | ~21.6 GB | High-end | Check price |
| RTX 5090 32 GB | Graphics cards | 32 GB VRAM | ~28.8 GB | High-end | Check price |
| MacBook Air with 16 GB | Macs | 16 GB unified memory | ~11.2 GB | Budget | Check price |
| Mac mini with 16 GB | Macs | 16 GB unified memory | ~11.2 GB | Budget | Check price |
| Mac mini with 24 GB | Macs | 24 GB unified memory | ~16.8 GB | Budget | Check price |
| MacBook Air with 24 GB | Macs | 24 GB unified memory | ~16.8 GB | Mid | Check price |
| MacBook Air with 32 GB | Macs | 32 GB unified memory | ~22.4 GB | Mid | Check price |
| Mac Studio with 64 GB | Macs | 64 GB unified memory | ~44.8 GB | High-end | Check price |
| Mac Studio with 128 GB | Macs | 128 GB unified memory | ~89.6 GB | High-end | Check price |
| RTX 4070 Laptop 8 GB | Powerful laptops | 8 GB VRAM | ~7.2 GB | Mid | Check price |
| MacBook Pro M4 Pro with 24 GB | Powerful laptops | 24 GB unified memory | ~16.8 GB | Mid | Check price |
| RTX 4090 Laptop 16 GB | Powerful laptops | 16 GB VRAM | ~14.4 GB | High-end | Check price |
| RTX 5090 Laptop 24 GB | Powerful laptops | 24 GB VRAM | ~21.6 GB | High-end | Check price |
| MacBook Pro with 36 GB | Powerful laptops | 36 GB unified memory | ~25.2 GB | High-end | Check price |
| MacBook Pro with 48 GB | Powerful laptops | 48 GB unified memory | ~33.6 GB | High-end | Check price |
| MacBook Pro M4 Max with 48 GB | Powerful laptops | 48 GB unified memory | ~33.6 GB | High-end | Check price |
How we pick
Usable memory is about 70% of a Mac's unified memory and 90% of a graphics card's VRAM. Models are the most downloaded open language models on Hugging Face that fit. Speed data: ModelFit (CC BY 4.0), modelled decode estimates for a 4-bit build at a 4K context, not measured benchmarks and not an endorsement by ModelFit.
As an Amazon Associate we earn from qualifying purchases.
Photo credits (Wikimedia Commons, resized): GeForce RTX 4060 graphics card: 极客湾Geekerwan, CC BY 3.0
_03.png){kind=link}