Can Tesla P4 8GB run gemma-4-12b-it?

NVIDIA · 8 GB GDDR5 · 192 GB/s bandwidth · Google · 11.95B · model ctx up to 256K

CUDA

No — gemma-4-12b-it at Q4 needs ≈ 8.77 GB even at 4K context, beyond the Tesla P4 8GB's 8 GB GDDR5. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 18.7 tok/s (estimated, batch 1). FP16 needs ≈ 27.29 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.

Fit & speed by quant and context

Quant	Context	VRAM needed	Fits?	tok/s (decode)
Q4	4K	8.77 GB	No	24.2 ± est.
Q4	8K default	9.96 GB	No	18.7 ± est.
Q4	32K	17.13 GB	No	6.3 ± est.
FP16	4K	26.09 GB	No	0.8 ± est.
FP16	8K default	27.29 GB	No	0.7 ± est.
FP16	32K	34.46 GB	No	—

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

Quant	Weights	KV cache	Overhead	Total needed	Tesla P4 8GB VRAM
Q4	6.57 GB	2.39 GB	1 GB	9.96 GB	8 GB
FP16	23.9 GB	2.39 GB	1 GB	27.29 GB	8 GB

Other GPUs that run gemma-4-12b-it

• B200 192GB SXM — ≈426.0 tok/s Q4 est.
• MI300X 192GB — ≈282.2 tok/s Q4 est.
• H200 141GB SXM5 — ≈255.6 tok/s Q4 est.
• H100 80GB SXM5 — ≈178.4 tok/s Q4 est.
• Gaudi 3 128GB — ≈174.5 tok/s Q4 est.
• A100 80GB SXM4 — ≈108.6 tok/s Q4 est.
• RTX 5090 32GB — ≈95.4 tok/s Q4 est.
• RTX 4090 24GB — ≈53.7 tok/s Q4 est.

All GPUs for gemma-4-12b-it →

Other models for the Tesla P4 8GB

• MiniCPM5-1B — ≈113.1 tok/s Q4 est.
• Qwen3.5-2B — ≈61.1 tok/s Q4 est.
• DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx — ≈53.1 tok/s Q4 est.
• Llama-3.2-3B-Instruct — ≈38.2 tok/s Q4 est.
• Qwen3-4B-Instruct-2507 — ≈30.5 tok/s Q4 est.
• NVIDIA-Nemotron-3-Nano-4B-BF16 — ≈30.5 tok/s Q4 est.
• Qwen3-4B-Thinking-2507 — ≈30.5 tok/s Q4 est.
• gemma-4-E2B-it — ≈24.0 tok/s Q4 est.

All models on the Tesla P4 8GB →