← Back to all models

TinyLlama 1.1B Chat v0.4

Chat model by Community · 1.1B parameters

Chip
Unified Memory
Bandwidth 307 GB/s
Available for Models ~21 GB

Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro

Runs Excellently

TinyLlama 1.1B Chat v0.4 fits comfortably in your 24 GB Mac using Q8_0 quantization, using 7% of your RAM.

~146 tok/s

Q8_0 · 1.7 GB · Estimated

Quantization Options

QuantizationMemorySpeedFits?
Q8_0 Recommended 1.7 GB~146 tok/s✓
Q6_K 1.5 GB~192 tok/s✓
Q5_K_M 1.3 GB~226 tok/s✓
Q4_K_M 1.2 GB~265 tok/s✓
Q3_K_M 1.1 GB~320 tok/s✓
Q2_K 1.0 GB~415 tok/s✓

Specifications

Parameters1.1B
Architecturellama
Context Length2K
CategoryChat
Formatgguf
Minimum RAM1 GB
HuggingFace Downloads5,463
View on HuggingFace →

Which Mac Can Run TinyLlama 1.1B Chat v0.4?

Minimum Mac

MacBook Air — M2 8GB

Q8_0 · ~48 tok/s · 22% RAM

MacQuanttok/sRAM %
Mac Studio · M3 Ultra 96GB Q8_0 ~390 2%
Mac Studio · M3 Ultra 256GB Q8_0 ~390 1%
Mac Studio · M3 Ultra 512GB Q8_0 ~390 0%
Mac Studio · M1 Ultra 64GB Q8_0 ~381 3%
Mac Studio · M1 Ultra 128GB Q8_0 ~381 1%
Mac Studio · M2 Ultra 64GB Q8_0 ~381 3%
Mac Studio · M2 Ultra 128GB Q8_0 ~381 1%
Mac Studio · M2 Ultra 192GB Q8_0 ~381 1%
MacBook Pro 14" · M5 Max 36GB Q8_0 ~292 5%
MacBook Pro 14" · M5 Max 48GB Q8_0 ~292 4%
MacBook Pro 14" · M5 Max 64GB Q8_0 ~292 3%
MacBook Pro 14" · M5 Max 128GB Q8_0 ~292 1%
MacBook Pro 16" · M5 Max 36GB Q8_0 ~292 5%
MacBook Pro 16" · M5 Max 48GB Q8_0 ~292 4%
MacBook Pro 16" · M5 Max 64GB Q8_0 ~292 3%
MacBook Pro 16" · M5 Max 128GB Q8_0 ~292 1%
MacBook Pro 14" · M4 Max 36GB Q8_0 ~260 5%
MacBook Pro 14" · M4 Max 48GB Q8_0 ~260 4%
MacBook Pro 14" · M4 Max 64GB Q8_0 ~260 3%
MacBook Pro 14" · M4 Max 128GB Q8_0 ~260 1%
MacBook Pro 16" · M4 Max 36GB Q8_0 ~260 5%
MacBook Pro 16" · M4 Max 48GB Q8_0 ~260 4%
MacBook Pro 16" · M4 Max 64GB Q8_0 ~260 3%
MacBook Pro 16" · M4 Max 128GB Q8_0 ~260 1%
Mac Studio · M4 Max 36GB Q8_0 ~260 5%
Mac Studio · M4 Max 48GB Q8_0 ~260 4%
Mac Studio · M4 Max 64GB Q8_0 ~260 3%
Mac Studio · M4 Max 128GB Q8_0 ~260 1%
MacBook Pro 14" · M1 Max 32GB Q8_0 ~190 5%
MacBook Pro 14" · M1 Max 64GB Q8_0 ~190 3%
MacBook Pro 14" · M2 Max 32GB Q8_0 ~190 5%
MacBook Pro 14" · M2 Max 64GB Q8_0 ~190 3%
MacBook Pro 14" · M2 Max 96GB Q8_0 ~190 2%
MacBook Pro 14" · M3 Max 36GB Q8_0 ~190 5%
MacBook Pro 14" · M3 Max 48GB Q8_0 ~190 4%
MacBook Pro 14" · M3 Max 64GB Q8_0 ~190 3%
MacBook Pro 14" · M3 Max 96GB Q8_0 ~190 2%
MacBook Pro 14" · M3 Max 128GB Q8_0 ~190 1%
MacBook Pro 16" · M1 Max 32GB Q8_0 ~190 5%
MacBook Pro 16" · M1 Max 64GB Q8_0 ~190 3%
MacBook Pro 16" · M2 Max 32GB Q8_0 ~190 5%
MacBook Pro 16" · M2 Max 64GB Q8_0 ~190 3%
MacBook Pro 16" · M2 Max 96GB Q8_0 ~190 2%
MacBook Pro 16" · M3 Max 36GB Q8_0 ~190 5%
MacBook Pro 16" · M3 Max 48GB Q8_0 ~190 4%
MacBook Pro 16" · M3 Max 64GB Q8_0 ~190 3%
MacBook Pro 16" · M3 Max 96GB Q8_0 ~190 2%
MacBook Pro 16" · M3 Max 128GB Q8_0 ~190 1%
Mac Studio · M1 Max 32GB Q8_0 ~190 5%
Mac Studio · M1 Max 64GB Q8_0 ~190 3%
Mac Studio · M2 Max 32GB Q8_0 ~190 5%
Mac Studio · M2 Max 64GB Q8_0 ~190 3%
Mac Studio · M2 Max 96GB Q8_0 ~190 2%
MacBook Pro 14" · M5 Pro 24GB Q8_0 ~146 7%
MacBook Pro 14" · M5 Pro 48GB Q8_0 ~146 4%
MacBook Pro 14" · M5 Pro 64GB Q8_0 ~146 3%
MacBook Pro 16" · M5 Pro 24GB Q8_0 ~146 7%
MacBook Pro 16" · M5 Pro 48GB Q8_0 ~146 4%
MacBook Pro 16" · M5 Pro 64GB Q8_0 ~146 3%
MacBook Pro 14" · M4 Pro 24GB Q8_0 ~130 7%
MacBook Pro 14" · M4 Pro 48GB Q8_0 ~130 4%
MacBook Pro 16" · M4 Pro 24GB Q8_0 ~130 7%
MacBook Pro 16" · M4 Pro 48GB Q8_0 ~130 4%
Mac mini · M4 Pro 24GB Q8_0 ~130 7%
Mac mini · M4 Pro 48GB Q8_0 ~130 4%
Mac mini · M4 Pro 64GB Q8_0 ~130 3%
MacBook Pro 14" · M1 Pro 16GB Q8_0 ~95 11%
MacBook Pro 14" · M1 Pro 32GB Q8_0 ~95 5%
MacBook Pro 14" · M2 Pro 16GB Q8_0 ~95 11%
MacBook Pro 14" · M2 Pro 32GB Q8_0 ~95 5%
MacBook Pro 16" · M1 Pro 16GB Q8_0 ~95 11%
MacBook Pro 16" · M1 Pro 32GB Q8_0 ~95 5%
MacBook Pro 16" · M2 Pro 16GB Q8_0 ~95 11%
MacBook Pro 16" · M2 Pro 32GB Q8_0 ~95 5%
Mac mini · M2 Pro 16GB Q8_0 ~95 11%
Mac mini · M2 Pro 32GB Q8_0 ~95 5%
MacBook Air · M5 16GB Q8_0 ~73 11%
MacBook Air · M5 24GB Q8_0 ~73 7%
MacBook Air · M5 32GB Q8_0 ~73 5%
MacBook Pro 14" · M5 16GB Q8_0 ~73 11%
MacBook Pro 14" · M5 24GB Q8_0 ~73 7%
MacBook Pro 14" · M5 32GB Q8_0 ~73 5%
MacBook Pro 14" · M3 Pro 18GB Q8_0 ~71 10%
MacBook Pro 14" · M3 Pro 36GB Q8_0 ~71 5%
MacBook Pro 16" · M3 Pro 18GB Q8_0 ~71 10%
MacBook Pro 16" · M3 Pro 36GB Q8_0 ~71 5%
MacBook Air · M4 16GB Q8_0 ~57 11%
MacBook Air · M4 24GB Q8_0 ~57 7%
MacBook Air · M4 32GB Q8_0 ~57 5%
MacBook Pro 14" · M4 16GB Q8_0 ~57 11%
MacBook Pro 14" · M4 24GB Q8_0 ~57 7%
MacBook Pro 14" · M4 32GB Q8_0 ~57 5%
Mac mini · M4 16GB Q8_0 ~57 11%
Mac mini · M4 24GB Q8_0 ~57 7%
Mac mini · M4 32GB Q8_0 ~57 5%
iMac · M4 16GB Q8_0 ~57 11%
iMac · M4 24GB Q8_0 ~57 7%
iMac · M4 32GB Q8_0 ~57 5%
MacBook Air · M2 8GB Q8_0 ~48 22%
MacBook Air · M2 16GB Q8_0 ~48 11%
MacBook Air · M2 24GB Q8_0 ~48 7%
MacBook Air · M3 8GB Q8_0 ~48 22%
MacBook Air · M3 16GB Q8_0 ~48 11%
MacBook Air · M3 24GB Q8_0 ~48 7%
MacBook Pro 14" · M3 8GB Q8_0 ~48 22%
MacBook Pro 14" · M3 16GB Q8_0 ~48 11%
MacBook Pro 14" · M3 24GB Q8_0 ~48 7%
Mac mini · M2 8GB Q8_0 ~48 22%
Mac mini · M2 16GB Q8_0 ~48 11%
Mac mini · M2 24GB Q8_0 ~48 7%
iMac · M3 8GB Q8_0 ~48 22%
iMac · M3 16GB Q8_0 ~48 11%
iMac · M3 24GB Q8_0 ~48 7%
MacBook Air · M1 8GB Q8_0 ~32 22%
MacBook Air · M1 16GB Q8_0 ~32 11%
Mac mini · M1 8GB Q8_0 ~32 22%
Mac mini · M1 16GB Q8_0 ~32 11%
iMac · M1 8GB Q8_0 ~32 22%
iMac · M1 16GB Q8_0 ~32 11%

Models similar to TinyLlama 1.1B Chat v0.4

Closest matches by use case and parameter count.

Run TinyLlama 1.1B Chat v0.4 locally on your Mac

ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.

Get ToolPiper — Free