Can Titan Xp 12GB run gemma-4-31B-it?

NVIDIA · 12 GB GDDR5X · 548 GB/s bandwidth · Google · 30.7B · model ctx up to 256K

CUDA

No — gemma-4-31B-it at Q4 needs ≈ 20.96 GB even at 4K context, beyond the Titan Xp 12GB's 12 GB GDDR5X. It would only run with heavy CPU/disk offload. Decode at Q4/8K: ≈ 8.1 tok/s (estimated, batch 1). FP16 needs ≈ 68.54 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	20.96 GB	No	10.6 ± est.
Q4	8K default	24.03 GB	No	8.1 ± est.
Q4	32K	42.45 GB	No	2.6 ± est.
FP16	4K	65.47 GB	No	—
FP16	8K default	68.54 GB	No	—
FP16	32K	86.96 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	Titan Xp 12GB VRAM
Q4	16.89 GB	6.14 GB	1 GB	24.03 GB	12 GB
FP16	61.4 GB	6.14 GB	1 GB	68.54 GB	12 GB

Other GPUs that run gemma-4-31B-it

• B200 192GB SXM — ≈165.8 tok/s Q4 est.
• MI300X 192GB — ≈109.9 tok/s Q4 est.
• H200 141GB SXM5 — ≈99.5 tok/s Q4 est.
• H100 80GB SXM5 — ≈69.4 tok/s Q4 est.
• Gaudi 3 128GB — ≈67.9 tok/s Q4 est.
• A100 80GB SXM4 — ≈42.3 tok/s Q4 est.
• RTX 5090 32GB — ≈37.1 tok/s Q4 est.
• RTX 6000 Ada 48GB — ≈19.9 tok/s Q4 est.

All GPUs for gemma-4-31B-it →

Other models for the Titan Xp 12GB

• MiniCPM5-1B — ≈322.9 tok/s Q4 est.
• Qwen3.5-2B — ≈174.4 tok/s Q4 est.
• DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx — ≈151.6 tok/s Q4 est.
• Llama-3.2-3B-Instruct — ≈109.0 tok/s Q4 est.
• Qwen3-4B-Instruct-2507 — ≈87.2 tok/s Q4 est.
• NVIDIA-Nemotron-3-Nano-4B-BF16 — ≈87.2 tok/s Q4 est.
• Qwen3-4B-Thinking-2507 — ≈87.2 tok/s Q4 est.
• gemma-4-E2B-it — ≈68.4 tok/s Q4 est.

All models on the Titan Xp 12GB →