Can MacBook Neo A18 Pro 8GB run Nanbeige4.2-3B?

Apple · 8 GB LPDDR5X · 60 GB/s bandwidth · Nanbeige · 4.0B · model ctx up to 128K

Fit & speed by quant and context

Fits = weights + KV(ctx) + 0.5 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).

VRAM breakdown at 8K context

Other GPUs that run Nanbeige4.2-3B

• B200 192GB SXM — ≈1913.5 tok/s Q4 est.
• MI300X 192GB — ≈1251.0 tok/s Q4 est.
• H200 141GB SXM5 — ≈1148.1 tok/s Q4 est.
• H100 80GB SXM5 — ≈801.3 tok/s Q4 est.
• Gaudi 3 128GB — ≈773.3 tok/s Q4 est.
• A100 80GB SXM4 — ≈487.7 tok/s Q4 est.
• RTX 5090 32GB — ≈428.6 tok/s Q4 est.
• RTX 4090 24GB — ≈219.1 tok/s Q4 est.

All GPUs for Nanbeige4.2-3B →

Other models for the MacBook Neo A18 Pro 8GB

• MiniCPM5-1B — ≈70.0 tok/s Q4 est.
• Qwen3.5-2B — ≈37.8 tok/s Q4 est.
• Llama-3.2-3B-Instruct — ≈23.6 tok/s Q4 est.
• Qwen3-4B-Instruct-2507 — ≈18.9 tok/s Q4 est.
• NVIDIA-Nemotron-3-Nano-4B-BF16 — ≈18.9 tok/s Q4 est.
• Qwen3-4B-Thinking-2507 — ≈18.9 tok/s Q4 est.
• gemma-4-E2B-it — ≈14.8 tok/s Q4 est.
• Mistral-7B-Instruct-v0.3 — ≈10.5 tok/s Q4 est.

All models on the MacBook Neo A18 Pro 8GB →