Llama 3.1 8B 4.9 GB
Meta's workhorse 8B — excellent all-around
MIN TIER
High
SMALLEST QUANT
Q2 · 2.7 GB
CONTEXT WINDOW
128K tokens
PARAMETERS
8.03B
QUANTIZATION OPTIONS
| Quant | File size | Quality | |
|---|---|---|---|
| FP16 | 16.1 GB | 100% | Best quality |
| Q8 | 8.5 GB | 95% | |
| Q6 | 6.2 GB | 85% | |
| Q5 | 5.3 GB | 78% | |
| Q4 | 4.6 GB | 70% | |
| Q3 | 3.4 GB | 58% | |
| Q2 | 2.7 GB | 42% |
DEVICE COMPATIBILITY
Runs on these devices (47)
🖥️
Mac Pro M2 Ultra 192GB
macOS FP16 · ~50 tok/s · 16.1 GB
Runs great 🖥️ Gaming PC (RTX 4080) 32GB
Windows Q8 · ~84 tok/s · 8.5 GB
Runs great 🖥️ Gaming PC (RTX 4090) 64GB
Windows FP16 · ~63 tok/s · 16.1 GB
Runs well 🖥️ Gaming PC (RTX 4070) 32GB
Windows Q8 · ~59 tok/s · 8.5 GB
Runs well 🖥️ Mac Studio M4 Max 64GB
macOS FP16 · ~34 tok/s · 16.1 GB
Runs great 🖥️ Gaming PC (RTX 3060) 32GB
Windows Q8 · ~42 tok/s · 8.5 GB
Runs well 💻 MacBook Pro M1 Max 64GB
macOS FP16 · ~25 tok/s · 16.1 GB
Runs great 💻 MacBook Pro M2 Max 64GB
macOS FP16 · ~25 tok/s · 16.1 GB
Runs great 💻 MacBook Pro M3 Max 96GB
macOS FP16 · ~25 tok/s · 16.1 GB
Runs great 🤖 Atom 1 64GB
Linux FP16 · ~17 tok/s · 16.1 GB
Runs great 🤖 Atom 1 128GB
Linux FP16 · ~17 tok/s · 16.1 GB
Runs great 🖥️ Mac Mini M4 Pro 48GB
macOS FP16 · ~17 tok/s · 16.1 GB
Runs great 💻 MacBook Pro M1 Max 32GB
macOS FP16 · ~25 tok/s · 16.1 GB
Runs well 💻 MacBook Pro M2 Max 32GB
macOS FP16 · ~25 tok/s · 16.1 GB
Runs well 💻 MacBook Pro M3 Max 36GB
macOS FP16 · ~25 tok/s · 16.1 GB
Runs well 💻 MacBook Pro M1 Pro 16GB
macOS Q8 · ~24 tok/s · 8.5 GB
Runs well 💻 MacBook Pro M2 Pro 16GB
macOS Q8 · ~24 tok/s · 8.5 GB
Runs well 🖥️ Mac Mini M2 Pro 16GB
macOS Q8 · ~24 tok/s · 8.5 GB
Runs well 💻 MacBook Pro M4 Pro 36GB
macOS FP16 · ~17 tok/s · 16.1 GB
Runs well 💻 MacBook Pro M3 Pro 18GB
macOS Q8 · ~18 tok/s · 8.5 GB
Runs well 💻 Snapdragon X Elite Laptop 16GB
Windows Q8 · ~16 tok/s · 8.5 GB
Runs well 💻 MacBook Air M4 16GB
macOS Q8 · ~14 tok/s · 8.5 GB
Runs well 💻 MacBook Pro M1 Pro 32GB
macOS FP16 · ~12 tok/s · 16.1 GB
Runs well 💻 MacBook Pro M2 Pro 32GB
macOS FP16 · ~12 tok/s · 16.1 GB
Runs well 🤖 Atom 1 32GB
Linux FP16 · ~13 tok/s · 16.1 GB
Runs well 🖥️ Mac Mini M2 Pro 32GB
macOS FP16 · ~12 tok/s · 16.1 GB
Runs well 🖥️ Mac Mini M4 16GB
macOS Q8 · ~14 tok/s · 8.5 GB
Runs well 💻 MacBook Air M3 16GB
macOS Q8 · ~12 tok/s · 8.5 GB
Runs well 💻 MacBook Pro M3 Pro 36GB
macOS FP16 · ~9 tok/s · 16.1 GB
Runs well 🎮 Steam Deck OLED 16GB
Linux Q8 · ~10 tok/s · 8.5 GB
Runs well 💻 MacBook Air M1 16GB
macOS Q8 · ~8 tok/s · 8.5 GB
Runs well 💻 MacBook Pro M1 16GB
macOS Q8 · ~8 tok/s · 8.5 GB
Runs well 🖥️ Mac Mini M1 16GB
macOS Q8 · ~8 tok/s · 8.5 GB
Runs well 🖥️ Mac Mini M4 32GB
macOS FP16 · ~7 tok/s · 16.1 GB
Runs well 🖥️ Mac Mini M4 Pro 24GB
macOS FP16 · ~17 tok/s · 16.1 GB
Tight fit 💻 MacBook Air M2 8GB
macOS Q5 · ~19 tok/s · 5.3 GB
Tight fit 🖥️ Mac Mini M2 8GB
macOS Q5 · ~19 tok/s · 5.3 GB
Tight fit 📱 iPad Pro M4 16GB
iOS Q6 · ~14 tok/s · 6.2 GB
Tight fit 💻 MacBook Air M1 8GB
macOS Q5 · ~13 tok/s · 5.3 GB
Tight fit 🖥️ Mac Mini M1 8GB
macOS Q5 · ~13 tok/s · 5.3 GB
Tight fit 📱 Pixel 9 Pro 16GB
Android Q6 · ~8 tok/s · 6.2 GB
Tight fit 📱 OnePlus 13 16GB
Android Q6 · ~9 tok/s · 6.2 GB
Tight fit 📱 Galaxy S25 Ultra 12GB
Android Q4 · ~12 tok/s · 4.6 GB
Tight fit 📱 iPhone 16 Pro 8GB
iOS Q3 · ~14 tok/s · 3.4 GB
Tight fit 🍓 Raspberry Pi 5 8GB
Linux Q5 · ~6 tok/s · 5.3 GB
Tight fit 📱 Galaxy S24 8GB
Android Q2 · ~16 tok/s · 2.7 GB
Tight fit 📱 iPhone 15 6GB
iOS Q2 · ~11 tok/s · 2.7 GB
Tight fit COMPARE WITH ANOTHER MODEL
RUN WITH THESE APPS
HOW TO RUN
Step-by-step run guides coming soon — check the apps above to get started today.