Can V100 16GB PCIe run Llama-3.2-3B-Instruct?

NVIDIA · 16 GB HBM2 · 900 GB/s bandwidth · Meta · 3.2B · model ctx up to 128K

Fit & speed by quant and context

Fits = weights + KV(ctx) + 1 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 Llama-3.2-3B-Instruct

• B200 192GB SXM — ≈2713.2 tok/s Q4 est.
• MI300X 192GB — ≈1700.2 tok/s Q4 est.
• H200 141GB SXM5 — ≈1627.9 tok/s Q4 est.
• H100 80GB SXM5 — ≈1136.1 tok/s Q4 est.
• Gaudi 3 128GB — ≈1050.9 tok/s Q4 est.
• A100 80GB SXM4 — ≈691.5 tok/s Q4 est.
• RTX 5090 32GB — ≈607.8 tok/s Q4 est.
• RTX 4090 24GB — ≈338.5 tok/s Q4 est.

All GPUs for Llama-3.2-3B-Instruct →

Other models for the V100 16GB PCIe

• MiniCPM5-1B — ≈895.6 tok/s Q4 est.
• Qwen3.5-2B — ≈483.6 tok/s Q4 est.
• DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx — ≈420.5 tok/s Q4 est.
• gpt-oss-20b — ≈268.7 tok/s Q4 est.
• gemma-4-26B-A4B-it — ≈254.5 tok/s Q4 est.
• Qwen3-4B-Instruct-2507 — ≈241.8 tok/s Q4 est.
• NVIDIA-Nemotron-3-Nano-4B-BF16 — ≈241.8 tok/s Q4 est.
• Qwen3-4B-Thinking-2507 — ≈241.8 tok/s Q4 est.

All models on the V100 16GB PCIe →