← Back to all models

Nemotron Cascade 2 96E A3B

General model by blascotobasco · 24.23B 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

Nemotron Cascade 2 96E A3B can run but will be tight at 77% of RAM. Consider a lower quantization or closing other apps.

~10tok/s
Q5_K_M18.6 GBEstimated

Alternative: Q4_K_M (16.1 GB, ~12 tok/s)

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

Specifications

Parameters24.2B
Architecturenemotron_h
Context Length4K
CategoryGeneral
Formatgguf
Minimum RAM13.5 GB
Licensenvidia-open-model-license

GGUF Sources

mradermacher
View on HuggingFace →

Quantization Options

QuantizationMemorySpeedFits?
Q8_0 27.5 GB~7 tok/s✗
Q6_K 21.5 GB~9 tok/s✗
Q5_K_M Recommended 18.6 GB~10 tok/s✓
Q4_K_M 16.1 GB~12 tok/s✓
Q3_K_M 13.7 GB~15 tok/s✓
Q2_K 11.1 GB~19 tok/s✓

Which Mac Can Run Nemotron Cascade 2 96E A3B?

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" — M1 Pro 16GB

Q2_K · ~12 tok/s · 69% RAM

MacQuanttok/sRAM %
Mac Studio · M5 Ultra 96GB Q8_0 ~27 29%
Mac Studio · M5 Ultra 256GB Q8_0 ~27 11%
Mac Studio · M5 Ultra 512GB Q8_0 ~27 5%
Mac Studio · M3 Ultra 96GB Q8_0 ~18 29%
Mac Studio · M3 Ultra 256GB Q8_0 ~18 11%
Mac Studio · M3 Ultra 512GB Q8_0 ~18 5%
Mac Studio · M1 Ultra 64GB Q8_0 ~17 43%
Mac Studio · M1 Ultra 128GB Q8_0 ~17 22%
Mac Studio · M2 Ultra 64GB Q8_0 ~17 43%
Mac Studio · M2 Ultra 128GB Q8_0 ~17 22%
Mac Studio · M2 Ultra 192GB Q8_0 ~17 14%
MacBook Pro 14" · M5 Max 36GB Q8_0 ~13 76%
MacBook Pro 14" · M5 Max 48GB Q8_0 ~13 57%
MacBook Pro 14" · M5 Max 64GB Q8_0 ~13 43%
MacBook Pro 14" · M5 Max 128GB Q8_0 ~13 22%
MacBook Pro 16" · M5 Max 36GB Q8_0 ~13 76%
MacBook Pro 16" · M5 Max 48GB Q8_0 ~13 57%
MacBook Pro 16" · M5 Max 64GB Q8_0 ~13 43%
MacBook Pro 16" · M5 Max 128GB Q8_0 ~13 22%
Mac Studio · M5 Max 36GB Q8_0 ~13 76%
Mac Studio · M5 Max 48GB Q8_0 ~13 57%
Mac Studio · M5 Max 64GB Q8_0 ~13 43%
Mac Studio · M5 Max 128GB Q8_0 ~13 22%
MacBook Pro 14" · M4 Max 36GB Q8_0 ~12 76%
MacBook Pro 14" · M4 Max 48GB Q8_0 ~12 57%
MacBook Pro 14" · M4 Max 64GB Q8_0 ~12 43%
MacBook Pro 14" · M4 Max 128GB Q8_0 ~12 22%
MacBook Pro 16" · M4 Max 36GB Q8_0 ~12 76%
MacBook Pro 16" · M4 Max 48GB Q8_0 ~12 57%
MacBook Pro 16" · M4 Max 64GB Q8_0 ~12 43%
MacBook Pro 16" · M4 Max 128GB Q8_0 ~12 22%
Mac Studio · M4 Max 36GB Q8_0 ~12 76%
Mac Studio · M4 Max 48GB Q8_0 ~12 57%
Mac Studio · M4 Max 64GB Q8_0 ~12 43%
Mac Studio · M4 Max 128GB Q8_0 ~12 22%
MacBook Pro 14" · M1 Max 32GB Q8_0 ~9 86%
MacBook Pro 14" · M1 Max 64GB Q8_0 ~9 43%
MacBook Pro 14" · M2 Max 32GB Q8_0 ~9 86%
MacBook Pro 14" · M2 Max 64GB Q8_0 ~9 43%
MacBook Pro 14" · M2 Max 96GB Q8_0 ~9 29%
MacBook Pro 14" · M3 Max 36GB Q8_0 ~9 76%
MacBook Pro 14" · M3 Max 48GB Q8_0 ~9 57%
MacBook Pro 14" · M3 Max 64GB Q8_0 ~9 43%
MacBook Pro 14" · M3 Max 96GB Q8_0 ~9 29%
MacBook Pro 14" · M3 Max 128GB Q8_0 ~9 22%
MacBook Pro 16" · M1 Max 32GB Q8_0 ~9 86%
MacBook Pro 16" · M1 Max 64GB Q8_0 ~9 43%
MacBook Pro 16" · M2 Max 32GB Q8_0 ~9 86%
MacBook Pro 16" · M2 Max 64GB Q8_0 ~9 43%
MacBook Pro 16" · M2 Max 96GB Q8_0 ~9 29%
MacBook Pro 16" · M3 Max 36GB Q8_0 ~9 76%
MacBook Pro 16" · M3 Max 48GB Q8_0 ~9 57%
MacBook Pro 16" · M3 Max 64GB Q8_0 ~9 43%
MacBook Pro 16" · M3 Max 96GB Q8_0 ~9 29%
MacBook Pro 16" · M3 Max 128GB Q8_0 ~9 22%
Mac Studio · M1 Max 32GB Q8_0 ~9 86%
Mac Studio · M1 Max 64GB Q8_0 ~9 43%
Mac Studio · M2 Max 32GB Q8_0 ~9 86%
Mac Studio · M2 Max 64GB Q8_0 ~9 43%
Mac Studio · M2 Max 96GB Q8_0 ~9 29%
MacBook Pro 14" · M5 Pro 48GB Q8_0 ~7 57%
MacBook Pro 14" · M5 Pro 64GB Q8_0 ~7 43%
MacBook Pro 16" · M5 Pro 48GB Q8_0 ~7 57%
MacBook Pro 16" · M5 Pro 64GB Q8_0 ~7 43%
Mac mini · M5 Pro 48GB Q8_0 ~7 57%
Mac mini · M5 Pro 64GB Q8_0 ~7 43%
MacBook Pro 14" · M4 Pro 48GB Q8_0 ~6 57%
MacBook Pro 16" · M4 Pro 48GB Q8_0 ~6 57%
Mac mini · M4 Pro 48GB Q8_0 ~6 57%
Mac mini · M4 Pro 64GB Q8_0 ~6 43%
MacBook Pro 14" · M1 Pro 32GB Q8_0 ~4 86%
MacBook Pro 14" · M2 Pro 32GB Q8_0 ~4 86%
MacBook Pro 16" · M1 Pro 32GB Q8_0 ~4 86%
MacBook Pro 16" · M2 Pro 32GB Q8_0 ~4 86%
Mac mini · M2 Pro 32GB Q8_0 ~4 86%
Mac mini · M6 32GB Q8_0 ~4 86%
MacBook Air · M5 32GB Q8_0 ~3 86%
MacBook Pro 14" · M5 32GB Q8_0 ~3 86%
MacBook Pro 14" · M3 Pro 36GB Q8_0 ~3 76%
MacBook Pro 16" · M3 Pro 36GB Q8_0 ~3 76%
MacBook Air · M4 32GB Q8_0 ~3 86%
MacBook Pro 14" · M4 32GB Q8_0 ~3 86%
Mac mini · M4 32GB Q8_0 ~3 86%
iMac · M4 32GB Q8_0 ~3 86%
MacBook Pro 14" · M1 Pro 16GB Q2_K ~12 69%
MacBook Pro 14" · M2 Pro 16GB Q2_K ~12 69%
MacBook Pro 16" · M1 Pro 16GB Q2_K ~12 69%
MacBook Pro 16" · M2 Pro 16GB Q2_K ~12 69%
Mac mini · M2 Pro 16GB Q2_K ~12 69%
Mac mini · M6 16GB Q2_K ~10 69%
MacBook Air · M5 16GB Q2_K ~9 69%
MacBook Pro 14" · M5 16GB Q2_K ~9 69%
MacBook Air · M4 16GB Q2_K ~7 69%
MacBook Pro 14" · M4 16GB Q2_K ~7 69%
Mac mini · M4 16GB Q2_K ~7 69%
iMac · M4 16GB Q2_K ~7 69%
MacBook Air · M2 16GB Q2_K ~6 69%
MacBook Air · M3 16GB Q2_K ~6 69%
MacBook Pro 14" · M3 16GB Q2_K ~6 69%
Mac mini · M2 16GB Q2_K ~6 69%
iMac · M3 16GB Q2_K ~6 69%
MacBook Air · M1 16GB Q2_K ~4 69%
Mac mini · M1 16GB Q2_K ~4 69%
iMac · M1 16GB Q2_K ~4 69%
MacBook Pro 14" · M5 Pro 24GB Q5_K_M ~10 77%
MacBook Pro 16" · M5 Pro 24GB Q5_K_M ~10 77%
Mac mini · M5 Pro 24GB Q5_K_M ~10 77%
MacBook Pro 14" · M4 Pro 24GB Q5_K_M ~9 77%
MacBook Pro 16" · M4 Pro 24GB Q5_K_M ~9 77%
Mac mini · M4 Pro 24GB Q5_K_M ~9 77%
MacBook Pro 14" · M3 Pro 18GB Q3_K_M ~7 76%
MacBook Pro 16" · M3 Pro 18GB Q3_K_M ~7 76%
Mac mini · M6 24GB Q5_K_M ~6 77%
MacBook Air · M5 24GB Q5_K_M ~5 77%
MacBook Pro 14" · M5 24GB Q5_K_M ~5 77%
MacBook Air · M4 24GB Q5_K_M ~4 77%
MacBook Pro 14" · M4 24GB Q5_K_M ~4 77%
Mac mini · M4 24GB Q5_K_M ~4 77%
iMac · M4 24GB Q5_K_M ~4 77%
MacBook Air · M2 24GB Q5_K_M ~3 77%
MacBook Air · M3 24GB Q5_K_M ~3 77%
MacBook Pro 14" · M3 24GB Q5_K_M ~3 77%
Mac mini · M2 24GB Q5_K_M ~3 77%
iMac · M3 24GB Q5_K_M ~3 77%
MacBook Air · M2 8GB — — 138%
MacBook Air · M3 8GB — — 138%
MacBook Pro 14" · M3 8GB — — 138%
Mac mini · M2 8GB — — 138%
iMac · M3 8GB — — 138%
MacBook Air · M1 8GB — — 138%
Mac mini · M1 8GB — — 138%
iMac · M1 8GB — — 138%

Models similar to Nemotron Cascade 2 96E A3B

Closest matches by use case and parameter count.

Run Nemotron Cascade 2 96E A3B locally on your Mac

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

Get ToolPiper free