← Back to all models

CodeLlama 34b Python hf

Coding model by codellama · 33.74B 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, Mac mini M5 Pro

Tight Fit

CodeLlama 34b Python hf can run but will be tight at 79% of RAM. Consider a lower quantization or closing other apps.

~10tok/s
Q3_K_M18.9 GBEstimated

Alternative: Q2_K (15.2 GB, ~14 tok/s)

Run it now. Download free No account, no caps, no terminal.

Specifications

Parameters33.7B
Architecturellama
Context Length4K
CategoryCoding
Formatgguf
Minimum RAM18.9 GB
HuggingFace Downloads1,279

GGUF Sources

mradermacher
View on HuggingFace →

Quantization Options

QuantizationMemorySpeedFits?
Q8_0 38.1 GB~5 tok/s✗
Q6_K 29.7 GB~6 tok/s✗
Q5_K_M 25.7 GB~7 tok/s✗
Q4_K_M 22.3 GB~9 tok/s✗
Q3_K_M Recommended 18.9 GB~10 tok/s✓
Q2_K 15.2 GB~14 tok/s✓

Which Mac Can Run CodeLlama 34b Python hf?

Affiliate disclosure: the shop icons in this table are Amazon affiliate links. As an Amazon Associate, ModelPiper earns from qualifying purchases. Every fit rating, quantization and tok/s figure below is computed from the hardware specs and is not influenced by that.

Minimum Mac

MacBook Pro 14" — M5 Max 48GB

Q8_0 · ~10 tok/s · 79% RAM

MacQuanttok/sRAM %
Mac Studio · M5 Ultra 96GB Q8_0 ~19 40%
Mac Studio · M5 Ultra 256GB Q8_0 ~19 15%
Mac Studio · M5 Ultra 512GB Q8_0 ~19 7%
Mac Studio · M3 Ultra 96GB Q8_0 ~13 40%
Mac Studio · M3 Ultra 256GB Q8_0 ~13 15%
Mac Studio · M3 Ultra 512GB Q8_0 ~13 7%
Mac Studio · M1 Ultra 64GB Q8_0 ~12 60%
Mac Studio · M1 Ultra 128GB Q8_0 ~12 30%
Mac Studio · M2 Ultra 64GB Q8_0 ~12 60%
Mac Studio · M2 Ultra 128GB Q8_0 ~12 30%
Mac Studio · M2 Ultra 192GB Q8_0 ~12 20%
MacBook Pro 14" · M5 Max 48GB Q8_0 ~10 79%
MacBook Pro 14" · M5 Max 64GB Q8_0 ~10 60%
MacBook Pro 14" · M5 Max 128GB Q8_0 ~10 30%
MacBook Pro 16" · M5 Max 48GB Q8_0 ~10 79%
MacBook Pro 16" · M5 Max 64GB Q8_0 ~10 60%
MacBook Pro 16" · M5 Max 128GB Q8_0 ~10 30%
Mac Studio · M5 Max 48GB Q8_0 ~10 79%
Mac Studio · M5 Max 64GB Q8_0 ~10 60%
Mac Studio · M5 Max 128GB Q8_0 ~10 30%
MacBook Pro 14" · M4 Max 48GB Q8_0 ~8 79%
MacBook Pro 14" · M4 Max 64GB Q8_0 ~8 60%
MacBook Pro 14" · M4 Max 128GB Q8_0 ~8 30%
MacBook Pro 16" · M4 Max 48GB Q8_0 ~8 79%
MacBook Pro 16" · M4 Max 64GB Q8_0 ~8 60%
MacBook Pro 16" · M4 Max 128GB Q8_0 ~8 30%
Mac Studio · M4 Max 48GB Q8_0 ~8 79%
Mac Studio · M4 Max 64GB Q8_0 ~8 60%
Mac Studio · M4 Max 128GB Q8_0 ~8 30%
MacBook Pro 14" · M1 Max 64GB Q8_0 ~6 60%
MacBook Pro 14" · M2 Max 64GB Q8_0 ~6 60%
MacBook Pro 14" · M2 Max 96GB Q8_0 ~6 40%
MacBook Pro 14" · M3 Max 48GB Q8_0 ~6 79%
MacBook Pro 14" · M3 Max 64GB Q8_0 ~6 60%
MacBook Pro 14" · M3 Max 96GB Q8_0 ~6 40%
MacBook Pro 14" · M3 Max 128GB Q8_0 ~6 30%
MacBook Pro 16" · M1 Max 64GB Q8_0 ~6 60%
MacBook Pro 16" · M2 Max 64GB Q8_0 ~6 60%
MacBook Pro 16" · M2 Max 96GB Q8_0 ~6 40%
MacBook Pro 16" · M3 Max 48GB Q8_0 ~6 79%
MacBook Pro 16" · M3 Max 64GB Q8_0 ~6 60%
MacBook Pro 16" · M3 Max 96GB Q8_0 ~6 40%
MacBook Pro 16" · M3 Max 128GB Q8_0 ~6 30%
Mac Studio · M1 Max 64GB Q8_0 ~6 60%
Mac Studio · M2 Max 64GB Q8_0 ~6 60%
Mac Studio · M2 Max 96GB Q8_0 ~6 40%
MacBook Pro 14" · M5 Pro 48GB Q8_0 ~5 79%
MacBook Pro 14" · M5 Pro 64GB Q8_0 ~5 60%
MacBook Pro 16" · M5 Pro 48GB Q8_0 ~5 79%
MacBook Pro 16" · M5 Pro 64GB Q8_0 ~5 60%
Mac mini · M5 Pro 48GB Q8_0 ~5 79%
Mac mini · M5 Pro 64GB Q8_0 ~5 60%
MacBook Pro 14" · M4 Pro 48GB Q8_0 ~4 79%
MacBook Pro 16" · M4 Pro 48GB Q8_0 ~4 79%
Mac mini · M4 Pro 48GB Q8_0 ~4 79%
Mac mini · M4 Pro 64GB Q8_0 ~4 60%
MacBook Pro 14" · M5 Max 36GB Q6_K ~13 83%
MacBook Pro 16" · M5 Max 36GB Q6_K ~13 83%
Mac Studio · M5 Max 36GB Q6_K ~13 83%
MacBook Pro 14" · M4 Max 36GB Q6_K ~11 83%
MacBook Pro 16" · M4 Max 36GB Q6_K ~11 83%
Mac Studio · M4 Max 36GB Q6_K ~11 83%
MacBook Pro 14" · M5 Pro 24GB Q3_K_M ~10 79%
MacBook Pro 16" · M5 Pro 24GB Q3_K_M ~10 79%
Mac mini · M5 Pro 24GB Q3_K_M ~10 79%
MacBook Pro 14" · M1 Max 32GB Q5_K_M ~10 80%
MacBook Pro 14" · M2 Max 32GB Q5_K_M ~10 80%
MacBook Pro 16" · M1 Max 32GB Q5_K_M ~10 80%
MacBook Pro 16" · M2 Max 32GB Q5_K_M ~10 80%
Mac Studio · M1 Max 32GB Q5_K_M ~10 80%
Mac Studio · M2 Max 32GB Q5_K_M ~10 80%
MacBook Pro 14" · M4 Pro 24GB Q3_K_M ~9 79%
MacBook Pro 16" · M4 Pro 24GB Q3_K_M ~9 79%
Mac mini · M4 Pro 24GB Q3_K_M ~9 79%
MacBook Pro 14" · M3 Max 36GB Q6_K ~8 83%
MacBook Pro 16" · M3 Max 36GB Q6_K ~8 83%
MacBook Pro 14" · M3 Pro 18GB Q2_K ~7 84%
MacBook Pro 16" · M3 Pro 18GB Q2_K ~7 84%
Mac mini · M6 24GB Q3_K_M ~6 79%
MacBook Air · M5 24GB Q3_K_M ~5 79%
MacBook Pro 14" · M5 24GB Q3_K_M ~5 79%
MacBook Pro 14" · M1 Pro 32GB Q5_K_M ~5 80%
MacBook Pro 14" · M2 Pro 32GB Q5_K_M ~5 80%
MacBook Pro 16" · M1 Pro 32GB Q5_K_M ~5 80%
MacBook Pro 16" · M2 Pro 32GB Q5_K_M ~5 80%
Mac mini · M2 Pro 32GB Q5_K_M ~5 80%
MacBook Air · M4 24GB Q3_K_M ~4 79%
MacBook Pro 14" · M4 24GB Q3_K_M ~4 79%
Mac mini · M4 24GB Q3_K_M ~4 79%
iMac · M4 24GB Q3_K_M ~4 79%
Mac mini · M6 32GB Q5_K_M ~4 80%
MacBook Air · M5 32GB Q5_K_M ~4 80%
MacBook Pro 14" · M5 32GB Q5_K_M ~4 80%
MacBook Air · M2 24GB Q3_K_M ~3 79%
MacBook Air · M3 24GB Q3_K_M ~3 79%
MacBook Pro 14" · M3 24GB Q3_K_M ~3 79%
Mac mini · M2 24GB Q3_K_M ~3 79%
iMac · M3 24GB Q3_K_M ~3 79%
MacBook Pro 14" · M3 Pro 36GB Q6_K ~3 83%
MacBook Pro 16" · M3 Pro 36GB Q6_K ~3 83%
MacBook Air · M4 32GB Q5_K_M ~3 80%
MacBook Pro 14" · M4 32GB Q5_K_M ~3 80%
Mac mini · M4 32GB Q5_K_M ~3 80%
iMac · M4 32GB Q5_K_M ~3 80%
MacBook Pro 14" · M1 Pro 16GB — — 95%
MacBook Pro 14" · M2 Pro 16GB — — 95%
MacBook Pro 16" · M1 Pro 16GB — — 95%
MacBook Pro 16" · M2 Pro 16GB — — 95%
Mac mini · M2 Pro 16GB — — 95%
Mac mini · M6 16GB — — 95%
MacBook Air · M5 16GB — — 95%
MacBook Pro 14" · M5 16GB — — 95%
MacBook Air · M4 16GB — — 95%
MacBook Pro 14" · M4 16GB — — 95%
Mac mini · M4 16GB — — 95%
iMac · M4 16GB — — 95%
MacBook Air · M2 8GB — — 190%
MacBook Air · M2 16GB — — 95%
MacBook Air · M3 8GB — — 190%
MacBook Air · M3 16GB — — 95%
MacBook Pro 14" · M3 8GB — — 190%
MacBook Pro 14" · M3 16GB — — 95%
Mac mini · M2 8GB — — 190%
Mac mini · M2 16GB — — 95%
iMac · M3 8GB — — 190%
iMac · M3 16GB — — 95%
MacBook Air · M1 8GB — — 190%
MacBook Air · M1 16GB — — 95%
Mac mini · M1 8GB — — 190%
Mac mini · M1 16GB — — 95%
iMac · M1 8GB — — 190%
iMac · M1 16GB — — 95%

Models similar to CodeLlama 34b Python hf

Closest matches by use case and parameter count.

Run CodeLlama 34b Python hf locally on your Mac

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

Get ToolPiper free