Can Tesla P4 8GB run gemma-3-27b-it?

NVIDIA · 8 GB GDDR5 · 192 GB/s bandwidth · Google · 27.4B · 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 gemma-3-27b-it

• B200 192GB SXM — ≈311.2 tok/s Q4 est.
• MI300X 192GB — ≈195.0 tok/s Q4 est.
• H200 141GB SXM5 — ≈186.7 tok/s Q4 est.
• H100 80GB SXM5 — ≈130.3 tok/s Q4 est.
• Gaudi 3 128GB — ≈120.5 tok/s Q4 est.
• A100 80GB SXM4 — ≈79.3 tok/s Q4 est.
• RTX 5090 32GB — ≈69.7 tok/s Q4 est.
• RTX 4090 24GB — ≈38.8 tok/s Q4 est.

All GPUs for gemma-3-27b-it →

Other models for the Tesla P4 8GB

• MiniCPM5-1B — ≈190.7 tok/s Q4 est.
• Qwen3.5-2B — ≈103.0 tok/s Q4 est.
• Llama-3.2-3B-Instruct — ≈64.4 tok/s Q4 est.
• Qwen3-4B-Instruct-2507 — ≈51.5 tok/s Q4 est.
• NVIDIA-Nemotron-3-Nano-4B-BF16 — ≈51.5 tok/s Q4 est.
• Qwen3-4B-Thinking-2507 — ≈51.5 tok/s Q4 est.
• gemma-4-E2B-it — ≈40.4 tok/s Q4 est.
• Mistral-7B-Instruct-v0.3 — ≈28.6 tok/s Q4 est.

All models on the Tesla P4 8GB →