Can Titan Xp 12GB run Qwen3-Coder-480B-A35B-Instruct?

NVIDIA · 12 GB GDDR5X · 548 GB/s bandwidth · Alibaba · 480.2B (active 35B) · MoE · model ctx up to 256K

CUDA

No — Qwen3-Coder-480B-A35B-Instruct at Q4 needs ≈ 268.61 GB even at 4K context, beyond the Titan Xp 12GB's 12 GB GDDR5X. It would only run with heavy CPU/disk offload. FP16 needs ≈ 968.4 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	268.61 GB	No	—
Q4	8K default	272.11 GB	No	—
Q4	32K	293.11 GB	No	—
FP16	4K	964.9 GB	No	—
FP16	8K default	968.4 GB	No	—
FP16	32K	989.4 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	264.11 GB	7.0 GB	1 GB	272.11 GB	12 GB
FP16	960.4 GB	7.0 GB	1 GB	968.4 GB	12 GB

Other GPUs that run Qwen3-Coder-480B-A35B-Instruct

• DGX Spark (GH200 480GB) — ≈9.1 tok/s Q4 est.

All GPUs for Qwen3-Coder-480B-A35B-Instruct →

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 →